# PostTrainBench v1.1 leaderboard

Coding 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/coding-post-train-bench11

Every model the catalog carries a published PostTrainBench v1.1 value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Coding |
| Measure | Weighted aggregate across four base models and seven benchmarks |
| Tasks | Post-training Qwen3 1.7B and 4B, SmolLM3 3B, and Gemma3 4B |
| Difficulty | Frontier agent evaluation |
| Published by | [PostTrainBench v1.1 leaderboard and methodology](https://posttrainbench.com/?version=v1.1) |

Post-training four base language models across seven weighted benchmarks, with ten hours and one H100 per run.

## PostTrainBench v1.1 ranking

15 models with a published PostTrainBench v1.1 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 | Weighted aggregate across four base models and seven benchmarks | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 49.3 | Observed 2026-10-23 · source benchlm:models |
| 2 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 45.3 | Observed 2026-10-23 · source benchlm:models |
| 3 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 44.3 | Observed 2026-10-23 · source benchlm:models |
| 4 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 40.2 | Observed 2026-10-23 · source benchlm:models |
| 5 | [MiniMax M3.1 Flash](https://modelscale.dev/models/minimax-m3-1-flash) | MiniMax | 39.3 | Observed 2026-10-23 · source benchlm:models |
| 6 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 36.2 | Observed 2026-10-23 · source benchlm:models |
| 7 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 35.0 | Observed 2026-10-23 · source benchlm:models |
| 8 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 32.9 | Observed 2026-10-23 · source benchlm:models |
| 9 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 32.0 | Observed 2026-10-23 · source benchlm:models |
| 10 | [GLM-5.2](https://modelscale.dev/models/glm-5-2) | Z.AI | 31.7 | Observed 2026-10-23 · source benchlm:models |
| 11 | [Claude Opus 4.7](https://modelscale.dev/models/claude-opus-4-7) | Anthropic | 28.6 | Observed 2026-10-23 · source benchlm:models |
| 12 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 27.2 | Observed 2026-10-23 · source benchlm:models |
| 13 | [Grok 4.5](https://modelscale.dev/models/grok-4-5) | xAI | 23.4 | Observed 2026-10-23 · source benchlm:models |
| 14 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 22.0 | Observed 2026-10-23 · source benchlm:models |
| 15 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 19.0 | Observed 2026-10-23 · 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.