Benchmark
PostTrainBench
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 27
- Scores recorded
- 35
- Sources
- 3
- IQ weight
- 1.58
Score distribution
- 33.7%
- Mean
- 36.5%
- Median
- 8%
- Std dev
- 22.6%
- 10th percentile
- 43.8%
- 90th percentile
- 16.5%
- Min
This benchmark has a weight of 1.58 for chat models, measured over 27 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Gemini 4 Argon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 45.3% |
| 2 | Claude Fable 5.1max· Epoch AI Benchmarking Hub data | 44.7% |
| 3 | Claude Fable 5.2max· Epoch AI Benchmarking Hub data | 44.6% |
| 4 | Claude Opus 5.5max· Epoch AI Benchmarking Hub data | 43.8% |
| 5 | GPT-6 Astramax· Epoch AI Benchmarking Hub data | 41.9% |
| 6 | Gemini 4 Carbonhigh· Epoch AI Benchmarking Hub data | 41% |
| 7 | Gemini 4 Argonhigh· Epoch AI Benchmarking Hub data | 40.4% |
| 8 | GLM 5.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 39.8% |
| 9 | GLM 5.3Claude Code 2.1.207 · max · 3-run weighted average · documented H100 fallback· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 39.8% |
| 10 | MiniMax M3.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 39.3% |
| 11 | GPT-6.1 Solmax· Epoch AI Benchmarking Hub data | 38.8% |
| 12 | Claude Fable 5max· Epoch AI Benchmarking Hub data | 37.3% |
| 13 | MiniMax M3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 37.1% |
| 14 | MiniMax M3Claude Code · Ralph-Loop · 12h· Reported by MiniMax Research· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.1% |
| 15 | GLM 5.3 Flashmax· Epoch AI Benchmarking Hub data | 36.8% |
| 16 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 36.6% |
| 17 | Kimi K3official Harbor · H100 · max effort · temp 1.0 · top_p 1.0· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 36.6% |
| 18 | Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 36.5% |
| 19 | Claude Opus 5· Epoch AI Benchmarking Hub data | 35.7% |
| 20 | Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35.6% |
| 21 | GLM 5.3max· Epoch AI Benchmarking Hub data | 34.5% |
| 22 | GLM 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34.3% |
| 23 | GLM 5.21M context · max effort · 128K output· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 34.3% |
| 24 | GPT-5.6 Solmax· Epoch AI Benchmarking Hub data | 31% |
| 25 | Claude Opus 4.8max· Epoch AI Benchmarking Hub data | 31% |
| 26 | Claude Opus 4.8high· Epoch AI Benchmarking Hub data | 30.7% |
| 27 | GLM 5.2max· Epoch AI Benchmarking Hub data | 30.4% |
| 28 | Claude Opus 4.7xhigh· Epoch AI Benchmarking Hub data | 24.3% |
| 29 | Muse Wonder 1.0xhigh· Epoch AI Benchmarking Hub data | 24.2% |
| 30 | GPT 5.5xhigh· Epoch AI Benchmarking Hub data | 23.9% |
| 31 | Grok 4.5high· Epoch AI Benchmarking Hub data | 22.6% |
| 32 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 18.3% |
| 33 | Gemini 3.1 Pro Preview· Epoch AI Benchmarking Hub data | 18.1% |
| 34 | GPT 5.4high· Epoch AI Benchmarking Hub data | 17.8% |
| 35 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 16.5% |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.