# Instruction Following leaderboard

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/instruction-following

How closely a model does what the prompt asks: the requested format, length and constraints, without drifting from them. A value the source did not publish stays unavailable rather than becoming a zero.

## Instruction Following leaderboard

286 source-backed models, ranked by instruction following score. Blended cost is the 75% input / 25% output mix used everywhere else on the site.

| Rank | Model | Provider | Access | Instruction Following | Overall | Blended $/1M (75% input / 25% output) | Evidence |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | [Grok 4.3](https://modelscale.dev/models/grok-4-3) | xAI | Proprietary | 97.1 | 46.7 | $1.56 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | Open Weight | 95.5 | 65.6 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 3 | [MAI-Thinking-1](https://modelscale.dev/models/mai-thinking-1) | Microsoft | Proprietary | 95.5 | 52.91 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 4 | [Inkling-Small](https://modelscale.dev/models/inkling-small) | Thinking Machines Lab | Open Weight | 94.1 | 48.9 | $0.79 | Observed 2026-11-21 · source benchlm:models |
| 5 | [DeepSeek V4 Pro](https://modelscale.dev/models/deepseek-v4-pro) | DeepSeek | Open Weight | 93.8 | 61.5 | $1.98 | Observed 2026-11-21 · source benchlm:models |
| 6 | [MiMo-V2.5-Pro](https://modelscale.dev/models/mimo-v2-5-pro) | Xiaomi | Proprietary | 93.8 | 55.8 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 7 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | Open Weight | 93.8 | 52.6 | $0.52 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GPT-5.2-Codex](https://modelscale.dev/models/gpt-5-2-codex) | OpenAI | Proprietary | 93.8 | 50.7 | $4.81 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GLM-5.1](https://modelscale.dev/models/glm-5-1) | Z.AI | Open Weight | 93.5 | 52.2 | $2.15 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | Proprietary | 93 | 69 | $11.25 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Muse Spark](https://modelscale.dev/models/muse-spark) | Meta | Proprietary | 93 | 53.6 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 12 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | Open Weight | 93 | 49.5 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.4 nano](https://modelscale.dev/models/gpt-5-4-nano) | OpenAI | Proprietary | 93 | 44.5 | $0.46 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | Proprietary | 92.8 | 59 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 15 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | Proprietary | 92.8 | 54.5 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 16 | [Qwen3.5-122B-A10B](https://modelscale.dev/models/qwen3-5-122b-a10b) | Alibaba | Open Weight | 92.8 | 43.3 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 17 | [MiniMax M2.7](https://modelscale.dev/models/minimax-m2-7) | MiniMax | Open Weight | 92.8 | 42 | $0.52 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Sage-A1.5](https://modelscale.dev/models/sage-a1-5) | InternScience | Open Weight | 92.7 | 55.4 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 19 | [Gemma 4 31B](https://modelscale.dev/models/gemma-4-31b) | Google | Open Weight | 92.6 | 43 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 20 | [Qwen3.5-27B](https://modelscale.dev/models/qwen3-5-27b) | Alibaba | Open Weight | 92.6 | 40 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 21 | [Qwen3.8-Omni-Flash](https://modelscale.dev/models/qwen3-8-omni-flash) | Alibaba | Proprietary | 92.5 | 59.5 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 22 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | Proprietary | 92.4 | 60.1 | $4.81 | Observed 2026-11-21 · source benchlm:models |
| 23 | [GPT-5.3 Codex](https://modelscale.dev/models/gpt-5-3-codex) | OpenAI | Proprietary | 92.4 | 54.9 | $4.81 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Qwen3.8-Flash-Next](https://modelscale.dev/models/qwen3-8-flash-next) | Alibaba | Open Weight | 92 | 60.8 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 25 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | Proprietary | 90.4 | 62.7 | $5.63 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Command A+](https://modelscale.dev/models/command-a-plus) | Cohere | Open Weight | 90.4 | 28.25 | $4.38 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | Proprietary | 90 | 61 | $4.50 | Observed 2026-11-21 · source benchlm:models |
| 28 | [dots3-note Preview](https://modelscale.dev/models/dots3-note-preview) | Dots Studio | Open Weight | 89.9 | 59.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 29 | [Gemma 4 12B](https://modelscale.dev/models/gemma-4-12b) | Google | Open Weight | 89.9 | 26.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 30 | [GLM-5.2](https://modelscale.dev/models/glm-5-2) | Z.AI | Open Weight | 89.6 | 59.2 | $2.15 | Observed 2026-11-21 · source benchlm:models |
| 31 | [GPT-5.4 mini](https://modelscale.dev/models/gpt-5-4-mini) | OpenAI | Proprietary | 89.6 | 50.4 | $1.69 | Observed 2026-11-21 · source benchlm:models |
| 32 | [GLM-5-Turbo](https://modelscale.dev/models/glm-5-turbo) | Z.AI | Proprietary | 89.5 | 45.5 | $1.90 | Observed 2026-11-21 · source benchlm:models |
| 33 | [GPT-5](https://modelscale.dev/models/gpt-5) | OpenAI | Proprietary | 89.4 | 54.1 | $3.44 | Observed 2026-11-21 · source benchlm:models |
| 34 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | Proprietary | 89.1 | 49.2 | $3.44 | Observed 2026-11-21 · source benchlm:models |
| 35 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | Proprietary | 88.9 | 73 | $8.00 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Qwen3.5-35B-A3B](https://modelscale.dev/models/qwen3-5-35b-a3b) | Alibaba | Open Weight | 88.6 | 34.7 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 37 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | Open Weight | 88.5 | 48.9 | $2.57 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Gemma 4 26B A4B](https://modelscale.dev/models/gemma-4-26b-a4b) | Google | Open Weight | 88.5 | 38.1 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 39 | [GLM-5](https://modelscale.dev/models/glm-5) | Z.AI | Open Weight | 88.3 | 45.8 | $1.55 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Qwen3.8-27B](https://modelscale.dev/models/qwen3-8-27b) | Alibaba | Open Weight | 87.8 | 55 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 41 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | Proprietary | 87.5 | 59.7 | $3.38 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Granite 4.2 8B](https://modelscale.dev/models/granite-4-2-8b) | IBM | Open Weight | 87.4 | 31.1 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 43 | [o3](https://modelscale.dev/models/o3) | OpenAI | Proprietary | 87.2 | 55.3 | $3.50 | Observed 2026-11-21 · source benchlm:models |
| 44 | [GPT-5.6 Terra](https://modelscale.dev/models/gpt-5-6-terra) | OpenAI | Proprietary | 86.9 | 65.9 | $4.50 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Solar Pro 3](https://modelscale.dev/models/solar-pro-3) | Upstage | Proprietary | 86.9 | 41.8 | $0.26 | Observed 2026-11-21 · source benchlm:models |
| 46 | [GPT-5 (medium)](https://modelscale.dev/models/gpt-5-medium) | OpenAI | Proprietary | 86.4 | 44.64 | Unavailable | Last good 2026-11-18 · source benchlm:models |
| 47 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | Proprietary | 85.9 | 59.8 | $4.50 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | Proprietary | 85.7 | 50.2 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 49 | [o1](https://modelscale.dev/models/o1) | OpenAI | Proprietary | 85.7 | 43.8 | $26.25 | Observed 2026-11-21 · source benchlm:models |
| 50 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | Open Weight | 85.6 | 43.9 | $1.20 | Observed 2026-11-21 · source benchlm:models |
| 51 | [GPT-5.1-Codex](https://modelscale.dev/models/gpt-5-1-codex) | OpenAI | Proprietary | 85.4 | 45.5 | $3.44 | Observed 2026-11-21 · source benchlm:models |
| 52 | [GPT-OSS 120B](https://modelscale.dev/models/gpt-oss-120b) | OpenAI | Open Weight | 84.1 | 35.4 | $0.16 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Mistral Medium 3.5 128B](https://modelscale.dev/models/mistral-medium-3-5-128b) | Mistral | Open Weight | 83.8 | 43.7 | $3.00 | Observed 2026-11-21 · source benchlm:models |
| 54 | [MiMo-V2-Pro](https://modelscale.dev/models/mimo-v2-pro) | Xiaomi | Proprietary | 83.8 | 41.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 55 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | Open Weight | 83.3 | 54.2 | $1.71 | Observed 2026-11-21 · source benchlm:models |
| 56 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | Open Weight | 82.6 | 43.3 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 57 | [Qwen3.6-27B](https://modelscale.dev/models/qwen3-6-27b) | Alibaba | Open Weight | 82.2 | 43.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 58 | [Muse Glimmer 30B](https://modelscale.dev/models/muse-glimmer-30b) | Meta | Open Weight | 81.9 | 44.4 | $0.64 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Mercury 2.5](https://modelscale.dev/models/mercury-2-5) | Inception | Proprietary | 81.9 | 39.6 | $0.0675 | Observed 2026-11-21 · source benchlm:models |
| 60 | [Step 3.7 Flash](https://modelscale.dev/models/step-3-7-flash) | StepFun | Open Weight | 81.8 | 48 | $0.44 | Observed 2026-11-21 · source benchlm:models |
| 61 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | Open Weight | 80.7 | 46.5 | $1.35 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Spark-X2.6-4B](https://modelscale.dev/models/spark-x2-6-4b) | SparkLLM | Open Weight | 79.1 | 40.6 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 63 | [GPT-OSS 20B](https://modelscale.dev/models/gpt-oss-20b) | OpenAI | Open Weight | 79 | 30 | $0.034 | Observed 2026-11-21 · source benchlm:models |
| 64 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | Open Weight | 78.1 | 39.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 65 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | Proprietary | 76.9 | 74.6 | $20.00 | Observed 2026-11-21 · source benchlm:models |
| 66 | [LFM2.5-24B-A2B](https://modelscale.dev/models/lfm2-5-24b-a2b) | LiquidAI | Open Weight | 76.5 | 41.5 | $0.33 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Kimi K2.7 Code](https://modelscale.dev/models/kimi-k2-7-code) | Moonshot AI | Open Weight | 76.4 | 52.2 | $1.71 | Observed 2026-11-21 · source benchlm:models |
| 68 | [Ling 3.0 Flash](https://modelscale.dev/models/ling-3-0-flash) | InclusionAI | Open Weight | 76 | 48.1 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 69 | [Nemotron 3 Nano Omni 30B A3B](https://modelscale.dev/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | Open Weight | 75.4 | 32.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 70 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | Proprietary | 75.2 | 66.6 | $10.00 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Ternary Bonsai 2 27B](https://modelscale.dev/models/ternary-bonsai-2-27b) | Prism ML | Open Weight | 74.8 | 46 | $0.18 | Observed 2026-11-21 · source benchlm:models |
| 72 | [GLM-5V-Turbo](https://modelscale.dev/models/glm-5v-turbo) | Z.AI | Proprietary | 73.8 | 38.8 | $1.90 | Observed 2026-11-21 · source benchlm:models |
| 73 | [LFM3-1.7B](https://modelscale.dev/models/lfm3-1-7b) | LiquidAI | Open Weight | 72.6 | 30.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 74 | [Nemotron 3.5 Lightning 30B A3B NVFP4](https://modelscale.dev/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | Open Weight | 72.2 | 27.5 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 75 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | Proprietary | 70.5 | 63.2 | $10.00 | Observed 2026-11-21 · source benchlm:models |
| 76 | [Claude Opus 4.5 Thinking](https://modelscale.dev/models/claude-opus-4-5-thinking) | Anthropic | Proprietary | 69.8 | 54.4 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 77 | [Nemotron 3.5 Super VL 120B A12B](https://modelscale.dev/models/nemotron-3-5-super-vl-120b-a12b) | NVIDIA | Open Weight | 67.5 | 46.3 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 78 | [Claude 4.1 Opus Thinking](https://modelscale.dev/models/claude-4-1-opus-thinking) | Anthropic | Proprietary | 66.5 | 37.77 | Unavailable | Last good 2026-11-18 · source benchlm:models |
| 79 | [Gemini 3 Flash](https://modelscale.dev/models/gemini-3-flash) | Google | Proprietary | 66 | 53.1 | $1.13 | Observed 2026-11-21 · source benchlm:models |
| 80 | [Grok 4](https://modelscale.dev/models/grok-4) | xAI | Proprietary | 64.2 | 48.1 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 81 | [MiMo-V2-Omni](https://modelscale.dev/models/mimo-v2-omni) | Xiaomi | Proprietary | 63.9 | 29.2 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 82 | [Grok 4.1 Fast (Reasoning)](https://modelscale.dev/models/grok-4-1-fast-reasoning) | xAI | Proprietary | 62.9 | 45.7 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 83 | [Grok 4 Fast (Reasoning)](https://modelscale.dev/models/grok-4-fast-reasoning) | xAI | Proprietary | 60 | 45.2 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 84 | [DeepSeek V3.2](https://modelscale.dev/models/deepseek-v3-2) | DeepSeek | Open Weight | 58.1 | 40 | $0.32 | Observed 2026-11-21 · source benchlm:models |
| 85 | [Gemini 2.5 Pro](https://modelscale.dev/models/gemini-2-5-pro) | Google | Proprietary | 57.7 | 43.1 | $3.44 | Observed 2026-11-21 · source benchlm:models |
| 86 | [Mistral Small 4](https://modelscale.dev/models/mistral-small-4) | Mistral | Open Weight | 57 | 25.74 | $0.26 | Observed 2026-11-21 · source benchlm:models |
| 87 | [Claude 4 Sonnet](https://modelscale.dev/models/claude-4-sonnet) | Anthropic | Proprietary | 53.4 | 41.1 | $6.00 | Observed 2026-11-21 · source benchlm:models |
| 88 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | Proprietary | 52.3 | 59.8 | $10.00 | Observed 2026-11-21 · source benchlm:models |
| 89 | [Gemma 4 E4B](https://modelscale.dev/models/gemma-4-e4b) | Google | Open Weight | 51.8 | 33.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 90 | [Qwen3 Max](https://modelscale.dev/models/qwen3-max) | Alibaba | Proprietary | 51.7 | 36.7 | $1.56 | Observed 2026-11-21 · source benchlm:models |
| 91 | [GPT-4.1](https://modelscale.dev/models/gpt-4-1) | OpenAI | Proprietary | 50.3 | 35.8 | $3.50 | Observed 2026-11-21 · source benchlm:models |
| 92 | [Llama 4 Maverick](https://modelscale.dev/models/llama-4-maverick) | Meta | Open Weight | 50.3 | 28.8 | $0.51 | Observed 2026-11-21 · source benchlm:models |
| 93 | [Hy3 Preview](https://modelscale.dev/models/hy3-preview) | Tencent | Open Weight | 49.2 | 38.5 | $0.29 | Observed 2026-11-21 · source benchlm:models |
| 94 | [DeepSeek V3.1 (Reasoning)](https://modelscale.dev/models/deepseek-v3-1-reasoning) | DeepSeek | Open Weight | 48.4 | 39.21 | Unavailable | Last good 2026-11-18 · source benchlm:models |
| 95 | [Kimi K2](https://modelscale.dev/models/kimi-k2) | Moonshot AI | Proprietary | 48.3 | 34.2 | $1.08 | Observed 2026-11-21 · source benchlm:models |
| 96 | [Grok Code Fast 1](https://modelscale.dev/models/grok-code-fast-1) | xAI | Proprietary | 48.2 | 39.8 | $0.53 | Observed 2026-11-21 · source benchlm:models |
| 97 | [Claude Sonnet 4.6](https://modelscale.dev/models/claude-sonnet-4-6) | Anthropic | Proprietary | 47.9 | 53.8 | $6.00 | Observed 2026-11-21 · source benchlm:models |
| 98 | [DeepSeek V3 0324](https://modelscale.dev/models/deepseek-v3-0324) | DeepSeek | Open Weight | 47.7 | 37.5 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 99 | [MiMo-V2-Flash](https://modelscale.dev/models/mimo-v2-flash) | Xiaomi | Open Weight | 46.2 | 39.1 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 100 | [DeepSeek-R1](https://modelscale.dev/models/deepseek-r1) | DeepSeek | Open Weight | 45.8 | 43.4 | $0.96 | Observed 2026-11-21 · source benchlm:models |
| 101 | [Llama 4 Scout](https://modelscale.dev/models/llama-4-scout) | Meta | Open Weight | 45.7 | 33.3 | $0.15 | Observed 2026-11-21 · source benchlm:models |
| 102 | [Mistral Medium 3](https://modelscale.dev/models/mistral-medium-3) | Mistral | Proprietary | 45.4 | 34.6 | $0.80 | Observed 2026-11-21 · source benchlm:models |
| 103 | [Gemini 2.5 Flash](https://modelscale.dev/models/gemini-2-5-flash) | Google | Proprietary | 45.1 | 44.1 | $0.85 | Observed 2026-11-21 · source benchlm:models |
| 104 | [GPT-4.1 mini](https://modelscale.dev/models/gpt-4-1-mini) | OpenAI | Proprietary | 44.1 | 33 | $0.70 | Observed 2026-11-21 · source benchlm:models |
| 105 | [Nova Pro](https://modelscale.dev/models/nova-pro) | Amazon | Proprietary | 43.9 | 20.99 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 106 | [Gemma 4 E2B](https://modelscale.dev/models/gemma-4-e2b) | Google | Open Weight | 43.8 | 33.9 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 107 | [DeepSeek V3.1](https://modelscale.dev/models/deepseek-v3-1) | DeepSeek | Open Weight | 43.5 | 39.7 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 108 | [GLM-4.5-Air](https://modelscale.dev/models/glm-4-5-air) | Z.AI | Proprietary | 43.2 | 39.6 | $0.43 | Observed 2026-11-21 · source benchlm:models |
| 109 | [GLM-4.6](https://modelscale.dev/models/glm-4-6) | Z.AI | Open Weight | 42.1 | 40.7 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 110 | [Grok 4.1 Fast](https://modelscale.dev/models/grok-4-1-fast) | xAI | Proprietary | 41.8 | 40.5 | $0.28 | Observed 2026-11-21 · source benchlm:models |
| 111 | [Mistral Large 3](https://modelscale.dev/models/mistral-large-3) | Mistral | Open Weight | 41.4 | 37.6 | $0.75 | Observed 2026-11-21 · source benchlm:models |
| 112 | [Claude 3 Haiku](https://modelscale.dev/models/claude-3-haiku) | Anthropic | Proprietary | 41.3 | 34.7 | $0.50 | Observed 2026-11-21 · source benchlm:models |
| 113 | [LFM2.5-2.6B](https://modelscale.dev/models/lfm2-5-2-6b) | LiquidAI | Open Weight | 40 | 39 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 114 | [DeepSeek V3](https://modelscale.dev/models/deepseek-v3) | DeepSeek | Open Weight | 39.6 | 37.2 | $0.48 | Observed 2026-11-21 · source benchlm:models |
| 115 | [Sarvam 105B](https://modelscale.dev/models/sarvam-105b) | Sarvam | Open Weight | 39.1 | 26 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 116 | [GPT-4o](https://modelscale.dev/models/gpt-4o) | OpenAI | Proprietary | 38.9 | 30.3 | $4.38 | Observed 2026-11-21 · source benchlm:models |
| 117 | [Ling 2.6 Flash](https://modelscale.dev/models/ling-2-6-flash) | InclusionAI | Open Weight | 38.6 | 47.8 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 118 | [LFM2.5-8B-A1B](https://modelscale.dev/models/lfm2-5-8b-a1b) | LiquidAI | Open Weight | 36.4 | 36.4 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 119 | [GPT-4.1 nano](https://modelscale.dev/models/gpt-4-1-nano) | OpenAI | Proprietary | 36 | 21.2 | $0.18 | Observed 2026-11-21 · source benchlm:models |
| 120 | [Gemma 3 27B](https://modelscale.dev/models/gemma-3-27b) | Google | Open Weight | 35.7 | 33.5 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 121 | [Mistral Large 2](https://modelscale.dev/models/mistral-large-2) | Mistral | Proprietary | 34.9 | 37.3 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 122 | [Qwen3-Omni-30B-A3B-Instruct](https://modelscale.dev/models/qwen3-omni-30b-a3b-instruct) | Alibaba | Open Weight | 34.9 | 28.07 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 123 | [GPT-4o mini](https://modelscale.dev/models/gpt-4o-mini) | OpenAI | Proprietary | 34.7 | 29.9 | $0.26 | Observed 2026-11-21 · source benchlm:models |
| 124 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | Proprietary | 31.9 | 54.4 | $10.00 | Observed 2026-11-21 · source benchlm:models |
| 125 | [Phi-4](https://modelscale.dev/models/phi-4) | Microsoft | Open Weight | 28.8 | 42.2 | $0.0875 | Observed 2026-11-21 · source benchlm:models |
| 126 | [Trinity-Large-Thinking](https://modelscale.dev/models/trinity-large-thinking) | Arcee AI | Open Weight | 28.8 | 30.5 | $0.41 | Observed 2026-11-21 · source benchlm:models |
| 127 | [DeepSeek R1 Distill Qwen 32B](https://modelscale.dev/models/deepseek-r1-distill-qwen-32b) | DeepSeek | Open Weight | 28.8 | 30.43 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 128 | [Granite-4.0-H-1B](https://modelscale.dev/models/granite-4-0-h-1b) | IBM | Open Weight | 28.8 | 28.78 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 129 | [Granite-4.0-350M](https://modelscale.dev/models/granite-4-0-350m) | IBM | Open Weight | 28.8 | 28.42 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 130 | [Granite-4.0-H-350M](https://modelscale.dev/models/granite-4-0-h-350m) | IBM | Open Weight | 28.8 | 28.42 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 131 | [Sarvam 30B](https://modelscale.dev/models/sarvam-30b) | Sarvam | Open Weight | 28.8 | 25 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 132 | [Granite-4.0-1B](https://modelscale.dev/models/granite-4-0-1b) | IBM | Open Weight | 28.5 | 38.06 | Unavailable | Last good 2026-09-18 · source benchlm:models |
| 133 | [ZAYA1-8B](https://modelscale.dev/models/zaya1-8b) | Zyphra | Open Weight | 24.4 | 24.5 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 134 | [MiniCPM5-1B](https://modelscale.dev/models/minicpm5-1b) | OpenBMB | Open Weight | 10.5 | 13.4 | Unavailable | Observed 2026-11-21 · source benchlm:models |
| 135 | [Claude Fable 5.2](https://modelscale.dev/models/claude-fable-5-2) | Anthropic | Proprietary | Unavailable | 93.2 | $16.00 | Unavailable · source benchlm:models |
| 136 | [GPT-6.2 Astra](https://modelscale.dev/models/gpt-6-2-astra) | OpenAI | Proprietary | Unavailable | 91 | $16.00 | Unavailable · source benchlm:models |
| 137 | [Gemini 4 Carbon](https://modelscale.dev/models/gemini-4-carbon) | Google | Proprietary | Unavailable | 88 | $4.00 | Unavailable · source benchlm:models |
| 138 | [Gemini 4 Neon](https://modelscale.dev/models/gemini-4-neon) | Google | Proprietary | Unavailable | 86.3 | $6.00 | Unavailable · source benchlm:models |
| 139 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | Proprietary | Unavailable | 83.2 | $20.00 | Unavailable · source benchlm:models |
| 140 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | Proprietary | Unavailable | 82.7 | $8.00 | Unavailable · source benchlm:models |
| 141 | [GPT-6.2 Sol](https://modelscale.dev/models/gpt-6-2-sol) | OpenAI | Proprietary | Unavailable | 82.6 | $4.00 | Unavailable · source benchlm:models |
| 142 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | Proprietary | Unavailable | 80.7 | $4.00 | Unavailable · source benchlm:models |
| 143 | [GPT-6.1 Terra](https://modelscale.dev/models/gpt-6-1-terra) | OpenAI | Proprietary | Unavailable | 80.4 | $2.00 | Unavailable · source benchlm:models |
| 144 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | Proprietary | Unavailable | 79.1 | $4.00 | Unavailable · source benchlm:models |
| 145 | [Gemini 4 Hydrogen](https://modelscale.dev/models/gemini-4-hydrogen) | Google | Proprietary | Unavailable | 78.8 | $3.00 | Unavailable · source benchlm:models |
| 146 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | Proprietary | Unavailable | 78.6 | $20.00 | Unavailable · source benchlm:models |
| 147 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | Proprietary | Unavailable | 77.9 | $4.00 | Unavailable · source benchlm:models |
| 148 | [Muse Wonder Full](https://modelscale.dev/models/muse-wonder-full) | Meta | Proprietary | Unavailable | 77.2 | Unavailable | Unavailable · source benchlm:models |
| 149 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | Proprietary | Unavailable | 74.9 | $10.00 | Unavailable · source benchlm:models |
| 150 | [Qwen4 Max](https://modelscale.dev/models/qwen4-max) | Alibaba | Proprietary | Unavailable | 74.5 | $2.25 | Unavailable · source benchlm:models |
| 151 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | Proprietary | Unavailable | 73.3 | $4.00 | Unavailable · source benchlm:models |
| 152 | [Muse Wonder](https://modelscale.dev/models/muse-wonder) | Meta | Proprietary | Unavailable | 71.1 | $8.00 | Unavailable · source benchlm:models |
| 153 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | Open Weight | Unavailable | 70.6 | $4.00 | Unavailable · source benchlm:models |
| 154 | [GPT-5.5 Pro](https://modelscale.dev/models/gpt-5-5-pro) | OpenAI | Proprietary | Unavailable | 70.1 | $67.50 | Unavailable · source benchlm:models |
| 155 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | Open Weight | Unavailable | 70 | $0.52 | Unavailable · source benchlm:models |
| 156 | [Hy4](https://modelscale.dev/models/hy4) | Tencent | Pending | Unavailable | 68.6 | $1.25 | Unavailable · source benchlm:models |
| 157 | [GPT-5.4 Pro](https://modelscale.dev/models/gpt-5-4-pro) | OpenAI | Proprietary | Unavailable | 68.3 | $67.50 | Unavailable · source benchlm:models |
| 158 | [Hy4 preview](https://modelscale.dev/models/hy4-preview) | Tencent | Open Weight | Unavailable | 68.3 | $1.25 | Unavailable · source benchlm:models |
| 159 | [MiniMax M3.1 Flash](https://modelscale.dev/models/minimax-m3-1-flash) | MiniMax | Proprietary | Unavailable | 68.1 | $0.26 | Unavailable · source benchlm:models |
| 160 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | Proprietary | Unavailable | 67.7 | $1.50 | Unavailable · source benchlm:models |
| 161 | [Ling 3.1 Flash](https://modelscale.dev/models/ling-3-1-flash) | InclusionAI | Open Weight | Unavailable | 66.8 | Unavailable | Unavailable · source benchlm:models |
| 162 | [Inkling 2 Small](https://modelscale.dev/models/inkling-2-small) | Thinking Machines Lab | Proprietary | Unavailable | 66.7 | $0.48 | Unavailable · source benchlm:models |
| 163 | [Gemini 3.7 Flash](https://modelscale.dev/models/gemini-3-7-flash) | Google | Proprietary | Unavailable | 66.4 | $1.50 | Unavailable · source benchlm:models |
| 164 | [Claude Opus 4.7 (Adaptive)](https://modelscale.dev/models/claude-opus-4-7-max) | Anthropic | Proprietary | Unavailable | 65.75 | $10.00 | Unavailable · source benchlm:models |
| 165 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | Open Weight | Unavailable | 65.5 | $6.00 | Unavailable · source benchlm:models |
| 166 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | Proprietary | Unavailable | 65.1 | $3.00 | Unavailable · source benchlm:models |
| 167 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | Open Weight | Unavailable | 63.7 | Unavailable | Unavailable · source benchlm:models |
| 168 | [Claude Haiku 5.5](https://modelscale.dev/models/claude-haiku-5-5) | Anthropic | Proprietary | Unavailable | 63.6 | $0.20 | Unavailable · source benchlm:models |
| 169 | [MiMo-V2.6-Pro](https://modelscale.dev/models/mimo-v2-6-pro) | Xiaomi | Open Weight | Unavailable | 63.5 | $0.54 | Unavailable · source benchlm:models |
| 170 | [GPT-5.2 Pro](https://modelscale.dev/models/gpt-5-2-pro) | OpenAI | Proprietary | Unavailable | 63.3 | $57.75 | Unavailable · source benchlm:models |
| 171 | [MiMo-V2.6-Flash](https://modelscale.dev/models/mimo-v2-6-flash) | Xiaomi | Open Weight | Unavailable | 63.2 | $0.18 | Unavailable · source benchlm:models |
| 172 | [Ornith-1.5-397B](https://modelscale.dev/models/ornith-1-5-397b) | Ornith AI | Open Weight | Unavailable | 63.2 | Unavailable | Unavailable · source benchlm:models |
| 173 | [Step 5 Preview](https://modelscale.dev/models/step-5-preview) | StepFun | Open Weight | Unavailable | 62.8 | $1.43 | Unavailable · source benchlm:models |
| 174 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | Open Weight | Unavailable | 62.13 | $1.98 | Unavailable · source benchlm:models |
| 175 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | Proprietary | Unavailable | 61.6 | $4.00 | Unavailable · source benchlm:models |
| 176 | [GPT-6 Luna](https://modelscale.dev/models/gpt-6-luna) | OpenAI | Proprietary | Unavailable | 61.3 | $0.20 | Unavailable · source benchlm:models |
| 177 | [Muse Ember](https://modelscale.dev/models/muse-ember) | Meta | Proprietary | Unavailable | 60.9 | $0.20 | Unavailable · source benchlm:models |
| 178 | [Gemini 3.6 Flash](https://modelscale.dev/models/gemini-3-6-flash) | Google | Proprietary | Unavailable | 60.4 | $1.50 | Unavailable · source benchlm:models |
| 179 | [Grok 4.5](https://modelscale.dev/models/grok-4-5) | xAI | Proprietary | Unavailable | 60.4 | $3.00 | Unavailable · source benchlm:models |
| 180 | [GPT-5.6 Luna](https://modelscale.dev/models/gpt-5-6-luna) | OpenAI | Proprietary | Unavailable | 60.2 | $0.45 | Unavailable · source benchlm:models |
| 181 | [Gemini 3 Pro Deep Think](https://modelscale.dev/models/gemini-3-pro-deep-think) | Google | Proprietary | Unavailable | 59.81 | Unavailable | Unavailable · source benchlm:models |
| 182 | [Claude Opus 4.6 (Adaptive)](https://modelscale.dev/models/claude-opus-4-6-thinking) | Anthropic | Proprietary | Unavailable | 59.8 | Unavailable | Unavailable · source benchlm:models |
| 183 | [Muse Spark 1.2](https://modelscale.dev/models/muse-spark-1-2) | Meta | Proprietary | Unavailable | 59.8 | $2.00 | Unavailable · source benchlm:models |
| 184 | [Muse Spark 1.1](https://modelscale.dev/models/muse-spark-1-1) | Meta | Proprietary | Unavailable | 59.5 | Unavailable | Unavailable · source benchlm:models |
| 185 | [Grok 4.1](https://modelscale.dev/models/grok-4-1) | xAI | Proprietary | Unavailable | 58.48 | Unavailable | Unavailable · source benchlm:models |
| 186 | [GLM-5 (Reasoning)](https://modelscale.dev/models/glm-5-reasoning) | Z.AI | Open Weight | Unavailable | 58.3 | $1.55 | Unavailable · source benchlm:models |
| 187 | [GLM-5.3-Flash](https://modelscale.dev/models/glm-5-3-flash) | Z.AI | Open Weight | Unavailable | 58.3 | Unavailable | Unavailable · source benchlm:models |
| 188 | [Qwen3.5 397B (Reasoning)](https://modelscale.dev/models/qwen3-5-397b-reasoning) | Alibaba | Open Weight | Unavailable | 58.03 | $1.35 | Unavailable · source benchlm:models |
| 189 | [GPT-5.2 Instant](https://modelscale.dev/models/gpt-5-2-instant) | OpenAI | Proprietary | Unavailable | 57.55 | $2.63 | Unavailable · source benchlm:models |
| 190 | [GPT-5.3 Instant](https://modelscale.dev/models/gpt-5-3-instant) | OpenAI | Proprietary | Unavailable | 57.44 | $4.81 | Unavailable · source benchlm:models |
| 191 | [GPT-5 (high)](https://modelscale.dev/models/gpt-5-high) | OpenAI | Proprietary | Unavailable | 57.19 | $3.44 | Unavailable · source benchlm:models |
| 192 | [Mistral Large 4](https://modelscale.dev/models/mistral-large-4) | Mistral | Open Weight | Unavailable | 56.8 | $1.05 | Unavailable · source benchlm:models |
| 193 | [DeepSeek V3.2 (Thinking)](https://modelscale.dev/models/deepseek-v3-2-thinking) | DeepSeek | Open Weight | Unavailable | 56.68 | $0.96 | Unavailable · source benchlm:models |
| 194 | [Qwen3 235B 2507 (Reasoning)](https://modelscale.dev/models/qwen3-235b-2507-reasoning) | Alibaba | Open Weight | Unavailable | 56.57 | Unavailable | Unavailable · source benchlm:models |
| 195 | [Kimi K2.5 (Reasoning)](https://modelscale.dev/models/kimi-k2-5-reasoning) | Moonshot AI | Open Weight | Unavailable | 56.53 | $1.20 | Unavailable · source benchlm:models |
| 196 | [Inkling 2 Mini](https://modelscale.dev/models/inkling-2-mini) | Thinking Machines Lab | Open Weight | Unavailable | 56 | $0.24 | Unavailable · source benchlm:models |
| 197 | [Muse Spark Open](https://modelscale.dev/models/muse-spark-open) | Meta | Open Weight | Unavailable | 55.8 | $2.00 | Unavailable · source benchlm:models |
| 198 | [GPT-5.3-Codex-Spark](https://modelscale.dev/models/gpt-5-3-codex-spark) | OpenAI | Proprietary | Unavailable | 55.49 | Unavailable | Unavailable · source benchlm:models |
| 199 | [Apodex 1.1](https://modelscale.dev/models/apodex-1-1) | Apodex | Proprietary | Unavailable | 54.8 | Unavailable | Unavailable · source benchlm:models |
| 200 | [Trinity-Large-Preview](https://modelscale.dev/models/trinity-large-preview) | Arcee AI | Open Weight | Unavailable | 54.53 | $0.44 | Unavailable · source benchlm:models |
| 201 | [Agents-A1](https://modelscale.dev/models/agents-a1) | InternScience | Open Weight | Unavailable | 54.37 | Unavailable | Unavailable · source benchlm:models |
| 202 | [Agents-A1-F16-GGUF](https://modelscale.dev/models/agents-a1-f16-gguf) | InternScience | Open Weight | Unavailable | 54.37 | Unavailable | Unavailable · source benchlm:models |
| 203 | [Agents-A1-FP8](https://modelscale.dev/models/agents-a1-fp8) | InternScience | Open Weight | Unavailable | 54.37 | Unavailable | Unavailable · source benchlm:models |
| 204 | [Agents-A1-Q4_K_M-GGUF](https://modelscale.dev/models/agents-a1-q4-k-m-gguf) | InternScience | Open Weight | Unavailable | 54.37 | Unavailable | Unavailable · source benchlm:models |
| 205 | [Agents-A1-Q8_0-GGUF](https://modelscale.dev/models/agents-a1-q8-0-gguf) | InternScience | Open Weight | Unavailable | 54.37 | Unavailable | Unavailable · source benchlm:models |
| 206 | [Qwen 3.6 Max (preview)](https://modelscale.dev/models/qwen3-6-max-preview) | Alibaba | Proprietary | Unavailable | 53.2 | Unavailable | Unavailable · source benchlm:models |
| 207 | [DeepSeek LLM 2.0](https://modelscale.dev/models/deepseek-llm-2-0) | DeepSeek | Open Weight | Unavailable | 53.14 | Unavailable | Unavailable · source benchlm:models |
| 208 | [Hy3](https://modelscale.dev/models/hy3) | Tencent | Open Weight | Unavailable | 52.1 | $0.23 | Unavailable · source benchlm:models |
| 209 | [Grok 4.20](https://modelscale.dev/models/grok-4-20-beta) | xAI | Proprietary | Unavailable | 51.6 | $1.56 | Unavailable · source benchlm:models |
| 210 | [Nemotron 3 Nano 30B](https://modelscale.dev/models/nemotron-3-nano-30b) | NVIDIA | Open Weight | Unavailable | 51.59 | Unavailable | Unavailable · source benchlm:models |
| 211 | [o3-pro](https://modelscale.dev/models/o3-pro) | OpenAI | Proprietary | Unavailable | 50.4 | $35.00 | Unavailable · source benchlm:models |
| 212 | [Gemini 3.5 Flash-Lite](https://modelscale.dev/models/gemini-3-5-flash-lite) | Google | Proprietary | Unavailable | 50.1 | $0.85 | Unavailable · source benchlm:models |
| 213 | [MiMo-V2.5](https://modelscale.dev/models/mimo-v2-5) | Xiaomi | Proprietary | Unavailable | 50.1 | Unavailable | Unavailable · source benchlm:models |
| 214 | [Quasar 438B](https://modelscale.dev/models/quasar-438b) | Multiverse Computing | Proprietary | Unavailable | 49.12 | $0.90 | Unavailable · source benchlm:models |
| 215 | [DeepSeek Coder 2.0](https://modelscale.dev/models/deepseek-coder-2-0) | DeepSeek | Open Weight | Unavailable | 48.97 | Unavailable | Unavailable · source benchlm:models |
| 216 | [Seed 1.6](https://modelscale.dev/models/seed-1-6) | ByteDance | Proprietary | Unavailable | 48.92 | Unavailable | Unavailable · source benchlm:models |
| 217 | [Ornith-1.5-35B-A3B](https://modelscale.dev/models/ornith-1-5-35b-a3b) | Ornith AI | Open Weight | Unavailable | 48.8 | Unavailable | Unavailable · source benchlm:models |
| 218 | [o4-mini (high)](https://modelscale.dev/models/o4-mini-high) | OpenAI | Proprietary | Unavailable | 48.68 | $1.93 | Unavailable · source benchlm:models |
| 219 | [DeepSeekMath V2](https://modelscale.dev/models/deepseekmath-v2) | DeepSeek | Open Weight | Unavailable | 48.58 | Unavailable | Unavailable · source benchlm:models |
| 220 | [Qwen2.5-1M](https://modelscale.dev/models/qwen2-5-1m) | Alibaba | Open Weight | Unavailable | 48.58 | Unavailable | Unavailable · source benchlm:models |
| 221 | [Seed-2.0-Lite](https://modelscale.dev/models/seed-2-0-lite) | ByteDance | Proprietary | Unavailable | 48.53 | Unavailable | Unavailable · source benchlm:models |
| 222 | [Ministral 3 14B (Reasoning)](https://modelscale.dev/models/ministral-3-14b-reasoning) | Mistral | Open Weight | Unavailable | 48.05 | $0.20 | Unavailable · source benchlm:models |
| 223 | [Step 3.5 Flash](https://modelscale.dev/models/step-3-5-flash) | StepFun | Open Weight | Unavailable | 47.7 | $0.15 | Unavailable · source benchlm:models |
| 224 | [Aion-2.0](https://modelscale.dev/models/aion-2-0) | Aion Labs | Proprietary | Unavailable | 47.37 | $1.00 | Unavailable · source benchlm:models |
| 225 | [Beam 1.0 501B-A23B](https://modelscale.dev/models/reflection-beam) | Reflection AI | Open Weight | Unavailable | 47.3 | Unavailable | Unavailable · source benchlm:models |
| 226 | [Ling 3.0 Flash VL](https://modelscale.dev/models/ling-3-0-flash-vl) | InclusionAI | Open Weight | Unavailable | 46.79 | Unavailable | Unavailable · source benchlm:models |
| 227 | [Claude Sonnet 4.5](https://modelscale.dev/models/claude-sonnet-4-5) | Anthropic | Proprietary | Unavailable | 46.6 | $6.00 | Unavailable · source benchlm:models |
| 228 | [Claude Sonnet 4.5 Thinking](https://modelscale.dev/models/claude-sonnet-4-5-thinking) | Anthropic | Proprietary | Unavailable | 46.6 | Unavailable | Unavailable · source benchlm:models |
| 229 | [Laguna S 2.1](https://modelscale.dev/models/laguna-s-2-1) | Poolside | Open Weight | Unavailable | 46.5 | $0.13 | Unavailable · source benchlm:models |
| 230 | [GPT-5.1-Codex-Max](https://modelscale.dev/models/gpt-5-1-codex-max) | OpenAI | Proprietary | Unavailable | 45.9 | $3.44 | Unavailable · source benchlm:models |
| 231 | [Claude 4.1 Opus](https://modelscale.dev/models/claude-4-1-opus) | Anthropic | Proprietary | Unavailable | 44.1 | $30.00 | Unavailable · source benchlm:models |
| 232 | [Qwen3.7 Flash](https://modelscale.dev/models/qwen3-7-flash) | Alibaba | Proprietary | Unavailable | 44 | $0.055 | Unavailable · source benchlm:models |
| 233 | [Z-1](https://modelscale.dev/models/z-1) | Z | Proprietary | Unavailable | 43.9 | Unavailable | Unavailable · source benchlm:models |
| 234 | [Seed 1.6 Flash](https://modelscale.dev/models/seed-1-6-flash) | ByteDance | Proprietary | Unavailable | 43.86 | Unavailable | Unavailable · source benchlm:models |
| 235 | [Mistral 8x7B](https://modelscale.dev/models/mistral-8x7b) | Mistral | Open Weight | Unavailable | 43.76 | Unavailable | Unavailable · source benchlm:models |
| 236 | [Qwen3.5 Plus](https://modelscale.dev/models/qwen3-5-plus) | Alibaba | Proprietary | Unavailable | 43.7 | $0.90 | Unavailable · source benchlm:models |
| 237 | [Nemotron 3.5 Bolt 74B-A9B](https://modelscale.dev/models/nemotron-3-5-bolt-74b-a9b) | NVIDIA | Open Weight | Unavailable | 43.6 | Unavailable | Unavailable · source benchlm:models |
| 238 | [o3-mini](https://modelscale.dev/models/o3-mini) | OpenAI | Proprietary | Unavailable | 43.6 | $1.93 | Unavailable · source benchlm:models |
| 239 | [Moonshot v1](https://modelscale.dev/models/moonshot-v1) | Moonshot AI | Proprietary | Unavailable | 43.57 | Unavailable | Unavailable · source benchlm:models |
| 240 | [o1-preview](https://modelscale.dev/models/o1-preview) | OpenAI | Proprietary | Unavailable | 43.5 | $26.25 | Unavailable · source benchlm:models |
| 241 | [Seed-2.0-Mini](https://modelscale.dev/models/seed-2-0-mini) | ByteDance | Proprietary | Unavailable | 43.38 | Unavailable | Unavailable · source benchlm:models |
| 242 | [Nemotron Ultra 253B](https://modelscale.dev/models/nemotron-ultra-253b) | NVIDIA | Open Weight | Unavailable | 43.18 | Unavailable | Unavailable · source benchlm:models |
| 243 | [GPT-5 mini](https://modelscale.dev/models/gpt-5-mini) | OpenAI | Proprietary | Unavailable | 41.6 | $0.69 | Unavailable · source benchlm:models |
| 244 | [Gemini 3.1 Flash-Lite](https://modelscale.dev/models/gemini-3-1-flash-lite) | Google | Proprietary | Unavailable | 41.4 | $0.56 | Unavailable · source benchlm:models |
| 245 | [Mixtral 8x22B Instruct v0.1](https://modelscale.dev/models/mixtral-8x22b-instruct-v0-1) | Mistral | Open Weight | Unavailable | 41.1 | Unavailable | Unavailable · source benchlm:models |
| 246 | [GPT-5 nano](https://modelscale.dev/models/gpt-5-nano) | OpenAI | Proprietary | Unavailable | 40.9 | $0.14 | Unavailable · source benchlm:models |
| 247 | [Grok 3 Mini](https://modelscale.dev/models/grok-3-mini) | xAI | Proprietary | Unavailable | 40.8 | $0.35 | Unavailable · source benchlm:models |
| 248 | [MiniMax M1 80k](https://modelscale.dev/models/minimax-m1-80k) | MiniMax | Proprietary | Unavailable | 40.8 | Unavailable | Unavailable · source benchlm:models |
| 249 | [Ministral 3 8B (Reasoning)](https://modelscale.dev/models/ministral-3-8b-reasoning) | Mistral | Open Weight | Unavailable | 39.23 | $0.15 | Unavailable · source benchlm:models |
| 250 | [GLM-4.5](https://modelscale.dev/models/glm-4-5) | Z.AI | Proprietary | Unavailable | 39 | $1.00 | Unavailable · source benchlm:models |
| 251 | [MiniMax M2.5](https://modelscale.dev/models/minimax-m2-5) | MiniMax | Proprietary | Unavailable | 39 | $0.52 | Unavailable · source benchlm:models |
| 252 | [Qwen2.5-VL-32B](https://modelscale.dev/models/qwen2-5-vl-32b) | Alibaba | Open Weight | Unavailable | 38.7 | Unavailable | Unavailable · source benchlm:models |
| 253 | [Llama 4 Behemoth](https://modelscale.dev/models/llama-4-behemoth) | Meta | Open Weight | Unavailable | 38.66 | Unavailable | Unavailable · source benchlm:models |
| 254 | [Claude 3.5 Sonnet](https://modelscale.dev/models/claude-3-5-sonnet) | Anthropic | Proprietary | Unavailable | 38.6 | $6.00 | Unavailable · source benchlm:models |
| 255 | [Grok 3 [Beta]](https://modelscale.dev/models/grok-3-beta) | xAI | Proprietary | Unavailable | 38.5 | Unavailable | Unavailable · source benchlm:models |
| 256 | [Ministral 3 3B (Reasoning)](https://modelscale.dev/models/ministral-3-3b-reasoning) | Mistral | Open Weight | Unavailable | 38.37 | $0.10 | Unavailable · source benchlm:models |
| 257 | [Mistral 8x7B v0.2](https://modelscale.dev/models/mistral-8x7b-v0-2) | Mistral | Open Weight | Unavailable | 37.99 | Unavailable | Unavailable · source benchlm:models |
| 258 | [GLM-4.7-Flash](https://modelscale.dev/models/glm-4-7-flash) | Z.AI | Open Weight | Unavailable | 37.5 | Unavailable | Unavailable · source benchlm:models |
| 259 | [Qwen3.5 Flash](https://modelscale.dev/models/qwen3-5-flash) | Alibaba | Proprietary | Unavailable | 37.4 | $0.18 | Unavailable · source benchlm:models |
| 260 | [o1-pro](https://modelscale.dev/models/o1-pro) | OpenAI | Proprietary | Unavailable | 36.32 | $262.50 | Unavailable · source benchlm:models |
| 261 | [Mercury 2](https://modelscale.dev/models/mercury-2) | Inception | Proprietary | Unavailable | 36.3 | $0.38 | Unavailable · source benchlm:models |
| 262 | [Ornith-1.5-9B](https://modelscale.dev/models/ornith-1-5-9b) | Ornith AI | Open Weight | Unavailable | 36.1 | Unavailable | Unavailable · source benchlm:models |
| 263 | [Gemini 1.5 Pro](https://modelscale.dev/models/gemini-1-5-pro) | Google | Proprietary | Unavailable | 35.3 | $2.19 | Unavailable · source benchlm:models |
| 264 | [Qwen3 235B 2507](https://modelscale.dev/models/qwen3-235b-2507) | Alibaba | Open Weight | Unavailable | 34.9 | Unavailable | Unavailable · source benchlm:models |
| 265 | [Claude Haiku 4.5](https://modelscale.dev/models/claude-haiku-4-5) | Anthropic | Proprietary | Unavailable | 33.8 | $2.00 | Unavailable · source benchlm:models |
| 266 | [Claude Haiku 4.5 Thinking](https://modelscale.dev/models/claude-haiku-4-5-thinking) | Anthropic | Proprietary | Unavailable | 33.8 | Unavailable | Unavailable · source benchlm:models |
| 267 | [GPT-4 Turbo](https://modelscale.dev/models/gpt-4-turbo) | OpenAI | Proprietary | Unavailable | 33.8 | $15.00 | Unavailable · source benchlm:models |
| 268 | [Nemotron 3 Super 100B](https://modelscale.dev/models/nemotron-3-super-100b) | NVIDIA | Open Weight | Unavailable | 32.3 | Unavailable | Unavailable · source benchlm:models |
| 269 | [Claude 3 Opus](https://modelscale.dev/models/claude-3-opus) | Anthropic | Proprietary | Unavailable | 30.5 | $30.00 | Unavailable · source benchlm:models |
| 270 | [Qwen2.5-72B](https://modelscale.dev/models/qwen2-5-72b) | Alibaba | Open Weight | Unavailable | 28.07 | Unavailable | Unavailable · source benchlm:models |
| 271 | [Llama 3.1 405B](https://modelscale.dev/models/llama-3-1-405b) | Meta | Open Weight | Unavailable | 27.53 | Unavailable | Unavailable · source benchlm:models |
| 272 | [Celeris-1](https://modelscale.dev/models/celeris-1) | Celeris | Proprietary | Unavailable | 27 | $0.33 | Unavailable · source benchlm:models |
| 273 | [Qwen2.5 Coder 32B Instruct](https://modelscale.dev/models/qwen2-5-coder-32b-instruct) | Alibaba | Open Weight | Unavailable | 25.94 | Unavailable | Unavailable · source benchlm:models |
| 274 | [Nemotron 3 Super 120B A12B](https://modelscale.dev/models/nemotron-3-super-120b-a12b) | NVIDIA | Open Weight | Unavailable | 25.9 | $0.16 | Unavailable · source benchlm:models |
| 275 | [Ministral 3 14B](https://modelscale.dev/models/ministral-3-14b) | Mistral | Open Weight | Unavailable | 24.85 | $0.20 | Unavailable · source benchlm:models |
| 276 | [LFM2-24B-A2B](https://modelscale.dev/models/lfm2-24b-a2b) | LiquidAI | Proprietary | Unavailable | 20.57 | Unavailable | Unavailable · source benchlm:models |
| 277 | [Llama 3 70B](https://modelscale.dev/models/llama-3-70b) | Meta | Open Weight | Unavailable | 20.36 | Unavailable | Unavailable · source benchlm:models |
| 278 | [Ministral 3 8B](https://modelscale.dev/models/ministral-3-8b) | Mistral | Open Weight | Unavailable | 19.95 | $0.15 | Unavailable · source benchlm:models |
| 279 | [LFM2.5-1.2B-Thinking](https://modelscale.dev/models/lfm2-5-1-2b-thinking) | LiquidAI | Proprietary | Unavailable | 19.33 | Unavailable | Unavailable · source benchlm:models |
| 280 | [LFM2.5-1.2B-Instruct](https://modelscale.dev/models/lfm2-5-1-2b-instruct) | LiquidAI | Proprietary | Unavailable | 19.08 | Unavailable | Unavailable · source benchlm:models |
| 281 | [Ministral 3 3B](https://modelscale.dev/models/ministral-3-3b) | Mistral | Open Weight | Unavailable | 18.78 | $0.10 | Unavailable · source benchlm:models |
| 282 | [Gemini 1.0 Pro](https://modelscale.dev/models/gemini-1-0-pro) | Google | Proprietary | Unavailable | 11.17 | Unavailable | Unavailable · source benchlm:models |
| 283 | [Nemotron-4 15B](https://modelscale.dev/models/nemotron-4-15b) | NVIDIA | Open Weight | Unavailable | 9.76 | Unavailable | Unavailable · source benchlm:models |
| 284 | [Mistral 7B v0.3](https://modelscale.dev/models/mistral-7b-v0-3) | Mistral | Open Weight | Unavailable | 7.05 | Unavailable | Unavailable · source benchlm:models |
| 285 | [Laguna XS.2](https://modelscale.dev/models/laguna-xs-2) | Poolside | Open Weight | Unavailable | 0.48 | Unavailable | Unavailable · source benchlm:models |
| 286 | [Laguna M.1](https://modelscale.dev/models/laguna-m-1) | Poolside | Proprietary | Unavailable | 0.31 | Unavailable | Unavailable · source benchlm:models |

74 of these rows are marked self-hosted by the source: open-weight models with no first-party hosted token rate. 11 of them show a hosted rate matched from another provider; the rest report an unavailable price rather than zero.
