PostTrainBench
The official leaderboard hasn’t scored a model released after Claude Fable 5 (June 2026). Labs report their own numbers for 8 newer models, such as GPT-6.2 Astra at 74.8%.
CLI agent gets a base model, one H100 and a time budget to post-train it for a target benchmark. Scored on normalized gain.
Known reward hacking (eval tampering, swapping in instruct models). Agent-as-judge added. Dataset link holds trajectories, not tasks.
- Released
- March 2026
- Kind
- Machine learning engineering
- Level
- Research frontier
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Refresh
- New versions replace it
- Run by
- Anyone
- In views
- Agents
- Strongest model tested
- GPT-6.2 Astra #1 on the capability index
- Last in a launch post
- October 2026
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
In the authors’ words
AI agents have become surprisingly proficient at software engineering over the past year, largely due to improvements in reasoning capabilities. This raises a deeper question: can these systems extend their capabilities to automate AI research itself? In this paper, we explore post-training, the critical phase that turns base LLMs into useful assistants. We introduce PostTrainBench to benchmark how well LLM agents can perform post-training autonomously under bounded compute constraints (10 hours on one H100 GPU). We ask frontier agents (e.g., Claude Code with Opus 4.6) to optimize the performance of a base LLM on a particular benchmark (e.g., Qwen3-4B on AIME). Importantly, we do not provide any predefined strategies to the agents and instead give them full autonomy to find necessary information on the web, run experiments, and curate data. We find that frontier agents make substantial progress but generally lag behind instruction-tuned LLMs from leading providers: 23.2% for the best agent vs. 51.1% for official instruction-tuned models. However, agents can exceed instruction-tuned models in targeted scenarios: GPT-5.1 Codex Max achieves 89% on BFCL with Gemma-3-4B vs. 67% for the official model. We also observe several failure modes worth flagging. Agents sometimes engage in reward hacking: training on the test set, downloading existing instruction-tuned checkpoints instead of training their own, and using API keys they find to generate synthetic data without authorization. These behaviors are concerning and highlight the importance of careful sandboxing as these systems become more capable. Overall, we hope PostTrainBench will be useful for tracking progress in AI R&D automation and for studying the risks that come with it. Website and code are available at https://posttrainbench.com/.
Claude Code + GLM-5.2 tops the leaderboard with 34.3% Claude Opus 4.8 leads with 34.1% among models released by June 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Every run is in the next chart. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. The best model on its own is Claude Opus 4.8, at 34.1%. Agents built around a model, such as Claude Code + GLM-5.2, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
GPT-6.2 Astra leads with 74.8%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
The newest model with a score here came out in June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 15 more
- 34.3 Claude Code + GLM-5.2
- 34.1 Claude Opus 4.8
- 30.7 Claude Fable 5
- 28.6 Claude Opus 4.7
- 28.4 GPT-5.5
- 28.2 GPT-5.4
- 24.8 Claude Opus 4.6
- 21.6 OpenCode + Gemini 3.1 Pro
- 21.4 GPT-5.2
- 19.7 GPT-5.1-Codex-Max
- 18.1
Gemini 3 Pro
- 17.8 GPT-5.3 Codex
- 17.3 OpenCode + Claude Opus 4.5
- 17.2 GPT-5.2 Codex
- 17.1 Claude Opus 4.5
- 16.4 Claude Sonnet 4.6
- 14.9 OpenCode + Gemini 3 Pro
- 13.9 OpenCode + GLM-5
- 10.3 OpenCode + Kimi K2.5
- 9.94 Claude Sonnet 4.5
- 9.50 OpenCode + MiniMax-M2.5
- 9.33 OpenCode + MiniMax-M2.1
- 7.65 OpenCode + GPT-5.1-Codex-Max
- 7.48 OpenCode + GLM-4.7
- 7.42 Claude Code + Qwen3-Max
- 7.25 OpenCode + Kimi K2 Thinking
- 1 Claude Code + GLM-5.2 max 34.3%
- 2 Claude Opus 4.8 max 34.1%
- 3 Claude Fable 5 max 30.7%
- 4 Claude Opus 4.7 xhigh 28.6%
- 5 GPT-5.5 xhigh, reprompted 28.4%
- 6 GPT-5.4 high, reprompted 28.2%
- 7 Claude Opus 4.6 1M context 24.8%
- 8 OpenCode + Gemini 3.1 Pro 21.6%
- 9 GPT-5.2 21.4%
- 10 GPT-5.1-Codex-Max 19.7%
- 11
Gemini 3 Pro 18.1%
- 12 GPT-5.3 Codex high 17.8%
- 13 OpenCode + Claude Opus 4.5 17.3%
- 14 GPT-5.2 Codex 17.2%
- 15 Claude Opus 4.5 17.1%
- 16 Claude Sonnet 4.6 16.4%
- 17 OpenCode + Gemini 3 Pro 14.9%
- 18 OpenCode + GLM-5 13.9%
- 19 OpenCode + Kimi K2.5 10.3%
- 20 Claude Sonnet 4.5 9.94%
- 21 OpenCode + MiniMax-M2.5 9.50%
- 22 OpenCode + MiniMax-M2.1 9.33%
- 23 OpenCode + GPT-5.1-Codex-Max 7.65%
- 24 OpenCode + GLM-4.7 7.48%
- 25 Claude Code + Qwen3-Max 7.42%
- 26 OpenCode + Kimi K2 Thinking 7.25%
Source: Official PostTrainBench leaderboard
- 1 Claude Opus 4.8 max 34.1%
- 2 Claude Fable 5 max 30.7%
- 3 Claude Opus 4.7 xhigh 28.6%
- 4 GPT-5.5 xhigh, reprompted 28.4%
- 5 GPT-5.4 high, reprompted 28.2%
- 6 Claude Opus 4.6 1M context 24.8%
- 7 GPT-5.2 21.4%
- 8 GPT-5.1-Codex-Max 19.7%
- 9
Gemini 3 Pro 18.1%
- 10 GPT-5.3 Codex high 17.8%
- 11 GPT-5.2 Codex 17.2%
- 12 Claude Opus 4.5 17.1%
- 13 Claude Sonnet 4.6 16.4%
- 14 Claude Sonnet 4.5 9.94%
Source: Official PostTrainBench leaderboard
- 74.8 GPT-6.2 Astra
- 45.3
Gemini 4 Argon
- 44.9 GPT-6.2 Sol
- 43.6
Muse Spark 1.3
- 39.8 GLM-5.3
- 37.1
MiniMax-M3
- 36.6 Kimi K3
- 34.3 GLM-5.2
- 34.1 Claude Opus 4.8
- 30.7 Claude Fable 5
- 28.6 Claude Opus 4.7
- 28.4 GPT-5.5
- 28.2 GPT-5.4
- 24.8 Claude Opus 4.6
- 21.4 GPT-5.2
- 19.7 GPT-5.1-Codex-Max
- 18.1
Gemini 3 Pro
- 17.8 GPT-5.3 Codex
- 17.2 GPT-5.2 Codex
- 17.1 Claude Opus 4.5
- 16.5
Seed2.1 Pro
- 16.4 Claude Sonnet 4.6
- 9.94 Claude Sonnet 4.5
- 1 GPT-6.2 Astra 74.8%
- 2
Gemini 4 Argon 45.3%
- 3 GPT-6.2 Sol 44.9%
- 4
Muse Spark 1.3 43.6%
- 5 GLM-5.3 39.8%
- 6
MiniMax-M3 37.1%
- 7 Kimi K3 36.6%
- 8 GLM-5.2 34.3%
- 9 Claude Opus 4.8 max 34.1%
- 10 Claude Fable 5 max 30.7%
- 11 Claude Opus 4.7 xhigh 28.6%
- 12 GPT-5.5 xhigh, reprompted 28.4%
- 13 GPT-5.4 high, reprompted 28.2%
- 14 Claude Opus 4.6 1M context 24.8%
- 15 GPT-5.2 21.4%
- 16 GPT-5.1-Codex-Max 19.7%
- 17
Gemini 3 Pro 18.1%
- 18 GPT-5.3 Codex high 17.8%
- 19 GPT-5.2 Codex 17.2%
- 20 Claude Opus 4.5 17.1%
- 21
Seed2.1 Pro 16.5%
- 22 Claude Sonnet 4.6 16.4%
- 23 Claude Sonnet 4.5 9.94%
Sources: Labs’ model cards and official PostTrainBench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Code + GLM-5.2 | 34.3% | max | Jun 2026 | Official leaderboard |
| 2 | Claude Opus 4.8 | 34.1% | max, Claude Code | May 2026 | Official leaderboard |
| 3 | Claude Fable 5 | 30.7% | max, Claude Code | Jun 2026 | Official leaderboard |
| 4 | Claude Opus 4.7 | 28.6% | xhigh, Claude Code | Apr 2026 | Official leaderboard |
| 5 | GPT-5.5 | 28.4% | xhigh, reprompted, Codex CLI | Apr 2026 | Official leaderboard |
| 6 | GPT-5.4 | 28.2% | high, reprompted, Codex CLI | Mar 2026 | Official leaderboard |
| 7 | Claude Opus 4.6 | 24.8% | 1M context, Claude Code | Feb 2026 | Official leaderboard |
| 8 | OpenCode + Gemini 3.1 Pro | 21.6% | Feb 2026 | Official leaderboard | |
| 9 | GPT-5.2 | 21.4% | Codex CLI | Dec 2025 | Official leaderboard |
| 10 | GPT-5.1-Codex-Max | 19.7% | Codex CLI | Nov 2025 | Official leaderboard |
| 11 | | 18.1% | Gemini CLI | Nov 2025 | Official leaderboard |
| 12 | GPT-5.3 Codex | 17.8% | high, Codex CLI | Feb 2026 | Official leaderboard |
| 13 | OpenCode + Claude Opus 4.5 | 17.3% | Nov 2025 | Official leaderboard | |
| 14 | GPT-5.2 Codex | 17.2% | Codex CLI | Dec 2025 | Official leaderboard |
| 15 | Claude Opus 4.5 | 17.1% | Claude Code | Nov 2025 | Official leaderboard |
| 16 | Claude Sonnet 4.6 | 16.4% | Claude Code | Feb 2026 | Official leaderboard |
| 17 | OpenCode + Gemini 3 Pro | 14.9% | Nov 2025 | Official leaderboard | |
| 18 | OpenCode + GLM-5 | 13.9% | Feb 2026 | Official leaderboard | |
| 19 | OpenCode + Kimi K2.5 | 10.3% | Jan 2026 | Official leaderboard | |
| 20 | Claude Sonnet 4.5 | 9.94% | Claude Code | Sep 2025 | Official leaderboard |
| 21 | OpenCode + MiniMax-M2.5 | 9.50% | Feb 2026 | Official leaderboard | |
| 22 | OpenCode + MiniMax-M2.1 | 9.33% | Dec 2025 | Official leaderboard | |
| 23 | OpenCode + GPT-5.1-Codex-Max | 7.65% | Nov 2025 | Official leaderboard | |
| 24 | OpenCode + GLM-4.7 | 7.48% | Dec 2025 | Official leaderboard | |
| 25 | Claude Code + Qwen3-Max | 7.42% | Sep 2025 | Official leaderboard | |
| 26 | OpenCode + Kimi K2 Thinking | 7.25% | Nov 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 34.1% | max, Claude Code | May 2026 | Official leaderboard |
| 2 | Claude Fable 5 | 30.7% | max, Claude Code | Jun 2026 | Official leaderboard |
| 3 | Claude Opus 4.7 | 28.6% | xhigh, Claude Code | Apr 2026 | Official leaderboard |
| 4 | GPT-5.5 | 28.4% | xhigh, reprompted, Codex CLI | Apr 2026 | Official leaderboard |
| 5 | GPT-5.4 | 28.2% | high, reprompted, Codex CLI | Mar 2026 | Official leaderboard |
| 6 | Claude Opus 4.6 | 24.8% | 1M context, Claude Code | Feb 2026 | Official leaderboard |
| 7 | GPT-5.2 | 21.4% | Codex CLI | Dec 2025 | Official leaderboard |
| 8 | GPT-5.1-Codex-Max | 19.7% | Codex CLI | Nov 2025 | Official leaderboard |
| 9 | | 18.1% | Gemini CLI | Nov 2025 | Official leaderboard |
| 10 | GPT-5.3 Codex | 17.8% | high, Codex CLI | Feb 2026 | Official leaderboard |
| 11 | GPT-5.2 Codex | 17.2% | Codex CLI | Dec 2025 | Official leaderboard |
| 12 | Claude Opus 4.5 | 17.1% | Claude Code | Nov 2025 | Official leaderboard |
| 13 | Claude Sonnet 4.6 | 16.4% | Claude Code | Feb 2026 | Official leaderboard |
| 14 | Claude Sonnet 4.5 | 9.94% | Claude Code | Sep 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6.2 Astra | 74.8% | Nov 2026 | Lab model card | |
| 2 | 45.3% | Oct 2026 | Lab model card | ||
| 3 | GPT-6.2 Sol | 44.9% | Nov 2026 | Lab model card | |
| 4 | 43.6% | Oct 2026 | Lab model card | ||
| 5 | GLM-5.3 | 39.8% | Aug 2026 | Lab model card | |
| 6 | 37.1% | Jun 2026 | Lab model card | ||
| 7 | Kimi K3 | 36.6% | Jul 2026 | Lab model card | |
| 8 | GLM-5.2 | 34.3% | Jun 2026 | Lab model card | |
| 9 | Claude Opus 4.8 | 34.1% | max, Claude Code | May 2026 | Official leaderboard |
| 10 | Claude Fable 5 | 30.7% | max, Claude Code | Jun 2026 | Official leaderboard |
| 11 | Claude Opus 4.7 | 28.6% | xhigh, Claude Code | Apr 2026 | Official leaderboard |
| 12 | GPT-5.5 | 28.4% | xhigh, reprompted, Codex CLI | Apr 2026 | Official leaderboard |
| 13 | GPT-5.4 | 28.2% | high, reprompted, Codex CLI | Mar 2026 | Official leaderboard |
| 14 | Claude Opus 4.6 | 24.8% | 1M context, Claude Code | Feb 2026 | Official leaderboard |
| 15 | GPT-5.2 | 21.4% | Codex CLI | Dec 2025 | Official leaderboard |
| 16 | GPT-5.1-Codex-Max | 19.7% | Codex CLI | Nov 2025 | Official leaderboard |
| 17 | 18.1% | Gemini CLI | Nov 2025 | Official leaderboard | |
| 18 | GPT-5.3 Codex | 17.8% | high, Codex CLI | Feb 2026 | Official leaderboard |
| 19 | GPT-5.2 Codex | 17.2% | Codex CLI | Dec 2025 | Official leaderboard |
| 20 | Claude Opus 4.5 | 17.1% | Claude Code | Nov 2025 | Official leaderboard |
| 21 | 16.5% | Jun 2026 | Lab model card | ||
| 22 | Claude Sonnet 4.6 | 16.4% | Claude Code | Feb 2026 | Official leaderboard |
| 23 | Claude Sonnet 4.5 | 9.94% | Claude Code | Sep 2025 | Official leaderboard |
Labs report scores for 9 models in their cards. Switch the scores above to rank them together.
Performance vs. runtime
Each point is one agent: the average time it spent post-training (of a 10-hour budget) against its average benchmark performance, with the Pareto frontier. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Average benchmark performance | Average time spent |
|---|---|---|---|
| Claude Code + GLM-5.2 | max, Claude Code | 34.3% | 8.35 h |
| Claude Opus 4.8 | max, Claude Code | 34.1% | 8.93 h |
| Claude Opus 4.8 | high, Claude Code | 33.8% | 9.27 h |
| Claude Opus 4.7 | xhigh, Claude Code | 28.6% | 7.57 h |
| GPT-5.5 | xhigh, reprompted, Codex CLI | 28.4% | 9.24 h |
| GPT-5.4 | high, reprompted, Codex CLI | 28.2% | 8.32 h |
| GPT-5.5 | xhigh, Codex CLI | 25% | 4.98 h |
| Claude Opus 4.6 | 1M context, Claude Code | 24.8% | 8.8 h |
| Claude Opus 4.6 | Claude Code | 23.2% | 9.66 h |
| OpenCode + Gemini 3.1 Pro | OpenCode | 21.6% | 4.05 h |
| GPT-5.2 | Codex CLI | 21.4% | 6.08 h |
| GPT-5.4 | high, Codex CLI | 20.2% | 1.77 h |
| GPT-5.1-Codex-Max | Codex CLI | 19.7% | 4.05 h |
| Gemini CLI | 18.1% | 6.6 h | |
| GPT-5.3 Codex | high, Codex CLI | 17.8% | 1.65 h |
| OpenCode + Claude Opus 4.5 | OpenCode | 17.3% | 6.88 h |
| GPT-5.2 Codex | Codex CLI | 17.2% | 2.43 h |
| Claude Opus 4.5 | Claude Code | 17.1% | 7.88 h |
| Claude Sonnet 4.6 | Claude Code | 16.4% | 6.83 h |
| OpenCode + Gemini 3 Pro | OpenCode | 14.9% | 6.06 h |
| OpenCode + GLM-5 | OpenCode | 13.9% | 3.56 h |
| GPT-5.3 Codex | med, Codex CLI | 13.8% | 0.89 h |
| OpenCode + Kimi K2.5 | OpenCode | 10.3% | 2.55 h |
| OpenCode + MiniMax-M2.5 | OpenCode | 9.5% | 2.98 h |
| OpenCode + MiniMax-M2.1 | OpenCode | 9.3% | 3.73 h |
| OpenCode + GPT-5.1-Codex-Max | OpenCode | 7.7% | 0.55 h |
| OpenCode + GLM-4.7 | OpenCode | 7.5% | 2.69 h |
| Claude Code + Qwen3-Max | Claude Code | 7.4% | 2.1 h |
| OpenCode + Kimi K2 Thinking | OpenCode | 7.3% | 1.37 h |
Performance vs. runtime
Each point is one agent: the average time it spent post-training (of a 10-hour budget) against its average benchmark performance, with the Pareto frontier. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Average benchmark performance | Average time spent |
|---|---|---|---|
| Claude Opus 4.8 | max, Claude Code | 34.1% | 8.93 h |
| Claude Opus 4.8 | high, Claude Code | 33.8% | 9.27 h |
| Claude Opus 4.7 | xhigh, Claude Code | 28.6% | 7.57 h |
| GPT-5.5 | xhigh, reprompted, Codex CLI | 28.4% | 9.24 h |
| GPT-5.4 | high, reprompted, Codex CLI | 28.2% | 8.32 h |
| GPT-5.5 | xhigh, Codex CLI | 25% | 4.98 h |
| Claude Opus 4.6 | 1M context, Claude Code | 24.8% | 8.8 h |
| Claude Opus 4.6 | Claude Code | 23.2% | 9.66 h |
| GPT-5.2 | Codex CLI | 21.4% | 6.08 h |
| GPT-5.4 | high, Codex CLI | 20.2% | 1.77 h |
| GPT-5.1-Codex-Max | Codex CLI | 19.7% | 4.05 h |
| Gemini CLI | 18.1% | 6.6 h | |
| GPT-5.3 Codex | high, Codex CLI | 17.8% | 1.65 h |
| GPT-5.2 Codex | Codex CLI | 17.2% | 2.43 h |
| Claude Opus 4.5 | Claude Code | 17.1% | 7.88 h |
| Claude Sonnet 4.6 | Claude Code | 16.4% | 6.83 h |
| GPT-5.3 Codex | med, Codex CLI | 13.8% | 0.89 h |
More effort adds a median 3 points
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official PostTrainBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Code + GLM-5.2 | max | Claude Code | 34.3% | ||
| Claude Opus 4.8 | max | Claude Code | 34.1% | ||
| Claude Opus 4.8 | high | Claude Code | 33.8% | ||
| Claude Fable 5 | max | Claude Code | 30.7% | ||
| Claude Opus 4.7 | xhigh | Claude Code | 28.6% | ||
| GPT-5.5 | xhigh, reprompted | Codex CLI | 28.4% | ||
| GPT-5.4 | high, reprompted | Codex CLI | 28.2% | ||
| GPT-5.5 | xhigh | Codex CLI | 25% | ||
| Claude Opus 4.6 | 1M context | Claude Code | 24.8% | ||
| Claude Opus 4.6 | Claude Code | 23.2% | |||
| OpenCode + Gemini 3.1 Pro | OpenCode | 21.6% | |||
| GPT-5.2 | Codex CLI | 21.4% | |||
| GPT-5.4 | high | Codex CLI | 20.2% | ||
| GPT-5.1-Codex-Max | Codex CLI | 19.7% | |||
| Gemini CLI | 18.1% | ||||
| GPT-5.3 Codex | high | Codex CLI | 17.8% | ||
| OpenCode + Claude Opus 4.5 | OpenCode | 17.3% | |||
| GPT-5.2 Codex | Codex CLI | 17.2% | |||
| Claude Opus 4.5 | Claude Code | 17.1% | |||
| Claude Sonnet 4.6 | Claude Code | 16.4% | |||
| OpenCode + Gemini 3 Pro | OpenCode | 14.9% | |||
| OpenCode + GLM-5 | OpenCode | 13.9% | |||
| GPT-5.3 Codex | med | Codex CLI | 13.8% | ||
| OpenCode + Kimi K2.5 | OpenCode | 10.3% | |||
| Claude Sonnet 4.5 | Claude Code | 9.94% | |||
| OpenCode + MiniMax-M2.5 | OpenCode | 9.50% | |||
| OpenCode + MiniMax-M2.1 | OpenCode | 9.33% | |||
| OpenCode + GPT-5.1-Codex-Max | OpenCode | 7.65% | |||
| OpenCode + GLM-4.7 | OpenCode | 7.48% | |||
| Claude Code + Qwen3-Max | Claude Code | 7.42% | |||
| OpenCode + Kimi K2 Thinking | OpenCode | 7.25% |
More effort adds a median 3 points
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official PostTrainBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 4.8 | max | Claude Code | 34.1% | ||
| Claude Opus 4.8 | high | Claude Code | 33.8% | ||
| Claude Fable 5 | max | Claude Code | 30.7% | ||
| Claude Opus 4.7 | xhigh | Claude Code | 28.6% | ||
| GPT-5.5 | xhigh, reprompted | Codex CLI | 28.4% | ||
| GPT-5.4 | high, reprompted | Codex CLI | 28.2% | ||
| GPT-5.5 | xhigh | Codex CLI | 25% | ||
| Claude Opus 4.6 | 1M context | Claude Code | 24.8% | ||
| Claude Opus 4.6 | Claude Code | 23.2% | |||
| GPT-5.2 | Codex CLI | 21.4% | |||
| GPT-5.4 | high | Codex CLI | 20.2% | ||
| GPT-5.1-Codex-Max | Codex CLI | 19.7% | |||
| Gemini CLI | 18.1% | ||||
| GPT-5.3 Codex | high | Codex CLI | 17.8% | ||
| GPT-5.2 Codex | Codex CLI | 17.2% | |||
| Claude Opus 4.5 | Claude Code | 17.1% | |||
| Claude Sonnet 4.6 | Claude Code | 16.4% | |||
| GPT-5.3 Codex | med | Codex CLI | 13.8% | ||
| Claude Sonnet 4.5 | Claude Code | 9.94% |
4 models have held number one on the official leaderboard since its release in March 2026 8 models have held number one with claims included since its release in March 2026
Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.
Sources: Official PostTrainBench leaderboard and labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official PostTrainBench leaderboard and labs’ model cards
4 labs put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Oct 13, 2026 | 45.3 | PostTrainBench (ML engineering) | |
| Aug 14, 2026 | GLM-5.3 | 39.8 | PostTrainBench |
| Jul 16, 2026 | Kimi K3 | 36.6 | PostTrainBench |
| Jun 16, 2026 | GLM-5.2 | 34.3 | PostTrainBench |
| Jun 1, 2026 | 37.1 | PostTrainBench |
13 system cards report it, from 5 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 17, 2026 | GPT-6.2 Sol system card | 44.9 | PostTrainBench Lite, mean share of performance gap closed, 12 tasks, includes three zero-score attempts (Table 5) | AI R&D risk |
| Nov 17, 2026 | GPT-6.2 Astra system card | 74.8 | PostTrainBench Lite, mean share of performance gap closed, 12 tasks (Table 5) | AI R&D risk |
| Oct 23, 2026 | | 43.6 | PostTrainBench, seven constituent benchmarks, Muse Spark 1.3 (Helpful) (Table 1, Table 5). Version not stated | AI R&D risk |
| Oct 13, 2026 | | 45.3 | PostTrainBench, ML engineering (results table, p.5) | Capabilities |
| Sep 3, 2026 | GPT-6 Astra system card | PostTrainBench Lite, mean reward vs output tokens, chart without printed numbers (Figure 55) | AI R&D risk | |
| Jul 27, 2026 | Kimi K3 technical report | 36.6 | PostTrainBench, official Harbor implementation, mean of 3 runs on H20 GPUs (Table 2) | AI R&D risk |
| Jul 9, 2026 | GPT-5.6 Terra system card | PostTrainBench Lite, mean reward by latency, chart without printed numbers (Figure 45, 9.1.3.4) | AI R&D risk | |
| Jul 9, 2026 | GPT-5.6 Sol system card | PostTrainBench Lite, mean reward by latency, chart without printed numbers (Figure 45, 9.1.3.4) | AI R&D risk | |
| Jul 9, 2026 | GPT-5.6 Luna system card | PostTrainBench Lite, mean reward by latency, chart without printed numbers (Figure 45, 9.1.3.4) | AI R&D risk | |
| Jun 25, 2026 | GPT-5.6 Terra system card | PostTrainBench Lite, mean reward by latency, chart without printed numbers (Figure 45, 9.1.3.4) | AI R&D risk | |
| Jun 25, 2026 | GPT-5.6 Sol system card | PostTrainBench Lite, mean reward by latency, chart without printed numbers (Figure 45, 9.1.3.4) | AI R&D risk | |
| Jun 25, 2026 | GPT-5.6 Luna system card | PostTrainBench Lite, mean reward by latency, chart without printed numbers (Figure 45, 9.1.3.4) | AI R&D risk | |
| Jun 23, 2026 | | 16.5 | PostTrainBench (Table 6) | AI R&D risk |
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
More in AI research
- PaperBench In use Agent replicates ICML 2024 papers from scratch. LLM judge grades against author-written hierarchical rubrics.
Qwen 3.8 Max 93%
- MLS-Bench In use Agent must invent one algorithmic change in an ML research scaffold whose gain transfers across settings. Scored relative to human baselines. Claude Fable 5.1 50.3%
- MLE-bench In use Kaggle-style ML engineering competitions. Agent trains models and is scored against competition leaderboards. GPT-6.2 Astra 96.1%
- PMPP-Hard In use Agents write GPU kernels for 69 tasks that must be correct, and on 48 of them also run within 1.25 times the reference time. The score is the area under the solved-tasks curve over a 10-hour budget, out of 690 task-hours. Kimi K3 0.71
- KernelBench In use Replace PyTorch operators with faster custom GPU kernels. Scored on correctness and speedup.
MiniMax-M3 28.8%
- OpenAI PRs Only in system cards Agents replicate internal OpenAI pull requests from a pre-PR branch and a prompt. Graded by hidden unit tests as pass@1. GPT-5.2 55%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (26 entries), launch posts (5 scores) and system cards (6 scores).
- Pass Models scored 23 models we track, plus 12 other entries on its leaderboard.
- Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
- Note Frontier models 2 of the top 10 have a score, which is fine for a retired test. The strongest tested is GPT-6.2 Astra (#1).
- Pass Headroom The best is 74.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on posttrainbench.com: 31 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.