# FrontierMath v2 (Tiers 1-3) leaderboard

Mathematics benchmark

> 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/benchmarks/math-frontier-math-v2-tiers13

FrontierMath v2 Tiers 1-3. Every model the catalog carries a published FrontierMath v2 (Tiers 1-3) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Mathematics |
| Measure | Python-enabled iterative mathematical problem solving |
| Tasks | 285 private advanced mathematics problems |
| Difficulty | From olympiad-plus to early research mathematics |
| Published by | [FrontierMath v2 benchmark hub](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |

Epoch AI's corrected v2 core FrontierMath suite of private advanced mathematics problems. Models can reason iteratively and use Python; scores are pass rates on the private set.

## FrontierMath v2 (Tiers 1-3) ranking

93 models with a published FrontierMath v2 (Tiers 1-3) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Python-enabled iterative mathematical problem solving | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Fable 5.2](https://modelscale.dev/models/claude-fable-5-2) | Anthropic | 95.088 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 93.684 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | 93.684 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6.2 Astra](https://modelscale.dev/models/gpt-6-2-astra) | OpenAI | 92.632 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 91.228 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6.1 Terra](https://modelscale.dev/models/gpt-6-1-terra) | OpenAI | 90.877 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Gemini 4 Carbon](https://modelscale.dev/models/gemini-4-carbon) | Google | 90.526 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 90.175 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | 89.825 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 89.000 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | 88.772 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Gemini 4 Hydrogen](https://modelscale.dev/models/gemini-4-hydrogen) | Google | 88.070 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.5 Pro](https://modelscale.dev/models/gpt-5-5-pro) | OpenAI | 87.719 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | 87.018 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 85.965 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 85.614 | Observed 2026-11-21 · source benchlm:models |
| 17 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 85.263 | Observed 2026-11-21 · source benchlm:models |
| 18 | [GPT-5.6 Terra](https://modelscale.dev/models/gpt-5-6-terra) | OpenAI | 84.900 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GPT-5.4 Pro](https://modelscale.dev/models/gpt-5-4-pro) | OpenAI | 82.456 | Observed 2026-11-21 · source benchlm:models |
| 20 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 80.000 | Observed 2026-11-21 · source benchlm:models |
| 21 | [GPT-6 Luna](https://modelscale.dev/models/gpt-6-luna) | OpenAI | 78.947 | Observed 2026-11-21 · source benchlm:models |
| 22 | [GPT-5.6 Luna](https://modelscale.dev/models/gpt-5-6-luna) | OpenAI | 78.600 | Observed 2026-11-21 · source benchlm:models |
| 23 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 78.596 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Claude Haiku 5.5](https://modelscale.dev/models/claude-haiku-5-5) | Anthropic | 75.088 | Observed 2026-11-21 · source benchlm:models |
| 25 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 74.737 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Muse Spark 1.3](https://modelscale.dev/models/muse-spark-1-3) | Meta | 74.035 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Gemini 3.7 Flash](https://modelscale.dev/models/gemini-3-7-flash) | Google | 71.579 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 70.175 | Observed 2026-11-21 · source benchlm:models |
| 29 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 68.772 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 68.421 | Observed 2026-11-21 · source benchlm:models |
| 31 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 67.400 | Observed 2026-11-21 · source benchlm:models |
| 32 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 67.368 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | 65.965 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | 65.965 | Observed 2026-11-21 · source benchlm:models |
| 35 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | 65.614 | Observed 2026-11-21 · source benchlm:models |
| 36 | [DeepSeek V4 Pro](https://modelscale.dev/models/deepseek-v4-pro) | DeepSeek | 64.561 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | 64.561 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 62.807 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 59.649 | Observed 2026-11-21 · source benchlm:models |
| 40 | [GLM-5.2](https://modelscale.dev/models/glm-5-2) | Z.AI | 59.206 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Gemini 3.6 Flash](https://modelscale.dev/models/gemini-3-6-flash) | Google | 58.947 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Grok 4.5](https://modelscale.dev/models/grok-4-5) | xAI | 57.193 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 57.193 | Observed 2026-11-21 · source benchlm:models |
| 44 | [GLM-5.3-Flash](https://modelscale.dev/models/glm-5-3-flash) | Z.AI | 55.789 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Kimi K2.7 Code](https://modelscale.dev/models/kimi-k2-7-code) | Moonshot AI | 54.035 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 52.982 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Gemini 3 Flash](https://modelscale.dev/models/gemini-3-flash) | Google | 51.228 | Observed 2026-11-21 · source benchlm:models |
| 47 | [GPT-5.4 mini](https://modelscale.dev/models/gpt-5-4-mini) | OpenAI | 51.228 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Inkling-Small](https://modelscale.dev/models/inkling-small) | Thinking Machines Lab | 46.316 | Observed 2026-11-21 · source benchlm:models |
| 50 | [GPT-5.4 nano](https://modelscale.dev/models/gpt-5-4-nano) | OpenAI | 44.912 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Grok 4.3](https://modelscale.dev/models/grok-4-3) | xAI | 42.807 | Observed 2026-11-21 · source benchlm:models |
| 52 | [Muse Spark](https://modelscale.dev/models/muse-spark) | Meta | 39.000 | Last good 2026-10-08 · source benchlm:models |
| 53 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 38.246 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 37.600 | Last good 2026-10-08 · source benchlm:models |
| 55 | [GLM-5.1](https://modelscale.dev/models/glm-5-1) | Z.AI | 36.842 | Observed 2026-11-21 · source benchlm:models |
| 56 | [o4-mini](https://modelscale.dev/models/o4-mini) | OpenAI | 36.140 | Observed 2026-11-21 · source benchlm:models |
| 56 | [o4-mini (high)](https://modelscale.dev/models/o4-mini-high) | OpenAI | 36.140 | Last good 2026-11-18 · source benchlm:models |
| 58 | [Qwen3.6-27B](https://modelscale.dev/models/qwen3-6-27b) | Alibaba | 35.088 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 34.386 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 34.386 | Observed 2026-11-21 · source benchlm:models |
| 61 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 33.333 | Observed 2026-11-21 · source benchlm:models |
| 61 | [o3](https://modelscale.dev/models/o3) | OpenAI | 33.333 | Observed 2026-11-21 · source benchlm:models |
| 63 | [Claude Sonnet 4.6](https://modelscale.dev/models/claude-sonnet-4-6) | Anthropic | 32.400 | Last good 2026-10-08 · source benchlm:models |
| 64 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | 31.034 | Last good 2026-10-08 · source benchlm:models |
| 65 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 27.900 | Last good 2026-10-08 · source benchlm:models |
| 66 | [Gemini 3.1 Flash-Lite](https://modelscale.dev/models/gemini-3-1-flash-lite) | Google | 27.719 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Gemini 3.5 Flash-Lite](https://modelscale.dev/models/gemini-3-5-flash-lite) | Google | 25.965 | Observed 2026-11-21 · source benchlm:models |
| 68 | [Gemini 2.5 Pro](https://modelscale.dev/models/gemini-2-5-pro) | Google | 24.561 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Claude Sonnet 4.5](https://modelscale.dev/models/claude-sonnet-4-5) | Anthropic | 23.860 | Observed 2026-11-21 · source benchlm:models |
| 70 | [Qwen 3.6 Max (preview)](https://modelscale.dev/models/qwen3-6-max-preview) | Alibaba | 23.103 | Last good 2026-10-08 · source benchlm:models |
| 71 | [DeepSeek V3.2](https://modelscale.dev/models/deepseek-v3-2) | DeepSeek | 22.100 | Last good 2026-10-08 · source benchlm:models |
| 72 | [Kimi K2](https://modelscale.dev/models/kimi-k2) | Moonshot AI | 21.404 | Last good 2026-10-08 · source benchlm:models |
| 73 | [Qwen3.5 Plus](https://modelscale.dev/models/qwen3-5-plus) | Alibaba | 21.034 | Last good 2026-10-08 · source benchlm:models |
| 74 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | 20.351 | Observed 2026-11-21 · source benchlm:models |
| 75 | [Grok 4](https://modelscale.dev/models/grok-4) | xAI | 19.655 | Last good 2026-10-08 · source benchlm:models |
| 76 | [Qwen3.7 Flash](https://modelscale.dev/models/qwen3-7-flash) | Alibaba | 19.298 | Observed 2026-11-21 · source benchlm:models |
| 77 | [Qwen3.5 Flash](https://modelscale.dev/models/qwen3-5-flash) | Alibaba | 18.246 | Observed 2026-11-21 · source benchlm:models |
| 78 | [GLM-5](https://modelscale.dev/models/glm-5) | Z.AI | 16.434 | Last good 2026-10-08 · source benchlm:models |
| 79 | [o1](https://modelscale.dev/models/o1) | OpenAI | 14.737 | Observed 2026-11-21 · source benchlm:models |
| 80 | [Qwen3 235B 2507 (Reasoning)](https://modelscale.dev/models/qwen3-235b-2507-reasoning) | Alibaba | 8.481 | Last good 2026-10-08 · source benchlm:models |
| 81 | [GPT-4.1 mini](https://modelscale.dev/models/gpt-4-1-mini) | OpenAI | 6.667 | Observed 2026-11-21 · source benchlm:models |
| 82 | [GPT-4.1](https://modelscale.dev/models/gpt-4-1) | OpenAI | 5.965 | Observed 2026-11-21 · source benchlm:models |
| 83 | [Claude Haiku 4.5](https://modelscale.dev/models/claude-haiku-4-5) | Anthropic | 5.903 | Last good 2026-10-08 · source benchlm:models |
| 84 | [Gemini 2.5 Flash](https://modelscale.dev/models/gemini-2-5-flash) | Google | 4.844 | Last good 2026-10-08 · source benchlm:models |
| 85 | [GLM-4.6](https://modelscale.dev/models/glm-4-6) | Z.AI | 3.819 | Last good 2026-10-08 · source benchlm:models |
| 86 | [Grok 3 [Beta]](https://modelscale.dev/models/grok-3-beta) | xAI | 3.793 | Last good 2026-10-08 · source benchlm:models |
| 87 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | 2.439 | Last good 2026-10-08 · source benchlm:models |
| 88 | [Claude 3.5 Sonnet](https://modelscale.dev/models/claude-3-5-sonnet) | Anthropic | 2.069 | Last good 2026-10-08 · source benchlm:models |
| 89 | [DeepSeek V3](https://modelscale.dev/models/deepseek-v3) | DeepSeek | 1.724 | Last good 2026-10-08 · source benchlm:models |
| 90 | [GPT-4.1 nano](https://modelscale.dev/models/gpt-4-1-nano) | OpenAI | 1.034 | Last good 2026-10-08 · source benchlm:models |
| 91 | [Llama 4 Maverick](https://modelscale.dev/models/llama-4-maverick) | Meta | 0.690 | Last good 2026-10-08 · source benchlm:models |
| 92 | [GPT-4o](https://modelscale.dev/models/gpt-4o) | OpenAI | 0.351 | Observed 2026-11-21 · source benchlm:models |
| 93 | [Llama 4 Scout](https://modelscale.dev/models/llama-4-scout) | Meta | 0.000 | Last good 2026-10-08 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
