Benchmark
GDP.pdf
Scores are percentages. Higher is better.
- Models measured
- 37
- Scores recorded
- 55
- Sources
- 3
- IQ weight
- 0.00
Score distribution
- 20%
- Mean
- 20.8%
- Median
- 22.1%
- Std dev
- 0.436%
- 10th percentile
- 35%
- 90th percentile
- 0.328%
- Min
This benchmark has a weight of 0.00 for chat models, measured over 37 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 | Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 81.6% |
| 2 | Claude Sonnet 5mean criteria pass rate · Python + image crop · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 81.6% |
| 3 | Claude Sonnet 4.6Python + image crop · Sonnet 5 card rerun · 128K max output· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 78.6% |
| 4 | Claude Sonnet 5mean criteria pass rate · no tools · base64 PDF · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.5% |
| 5 | Claude Sonnet 4.6no tools · Sonnet 5 card rerun · 128K max output· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.9% |
| 6 | Gemini 4 Carbonhigh· Epoch AI Benchmarking Hub data | 56.4% |
| 7 | Muse Wonder 1.0max· Epoch AI Benchmarking Hub data | 54.8% |
| 8 | Gemini 4 Hydrogenxhigh· Epoch AI Benchmarking Hub data | 54.2% |
| 9 | Gemini 4 Argonhigh· Epoch AI Benchmarking Hub data | 53.6% |
| 10 | Gemini 4 Neonhigh· Epoch AI Benchmarking Hub data | 53.4% |
| 11 | Muse Spark 1.3max· Epoch AI Benchmarking Hub data | 53% |
| 12 | Claude Fable 5.2max· Epoch AI Benchmarking Hub data | 51.8% |
| 13 | GPT-6.1 Solmax· Epoch AI Benchmarking Hub data | 51.6% |
| 14 | Claude Sonnet 5.5max· Epoch AI Benchmarking Hub data | 51.2% |
| 15 | GPT-6 Astramax· Epoch AI Benchmarking Hub data | 50.4% |
| 16 | Claude Fable 5.1max· Epoch AI Benchmarking Hub data | 49.4% |
| 17 | GPT-6.2 Astramax· Epoch AI Benchmarking Hub data | 49.2% |
| 18 | Muse Ember 1.0max· Epoch AI Benchmarking Hub data | 49.2% |
| 19 | Claude Opus 5.5max· Epoch AI Benchmarking Hub data | 48.8% |
| 20 | GPT-6.2 Solmax· Epoch AI Benchmarking Hub data | 48.8% |
| 21 | Grok 4.7xhigh· Epoch AI Benchmarking Hub data | 48.8% |
| 22 | Kimi K3.1 Promax· Epoch AI Benchmarking Hub data | 46.6% |
| 23 | Gemini 3.8 Flashhigh· Epoch AI Benchmarking Hub data | 44.2% |
| 24 | Inkling 2 Smallxhigh· Epoch AI Benchmarking Hub data | 43.6% |
| 25 | Qwen3.8 Maxxhigh· Epoch AI Benchmarking Hub data | 42.8% |
| 26 | Kimi K3max· Epoch AI Benchmarking Hub data | 39.8% |
| 27 | GLM 5.3max· Epoch AI Benchmarking Hub data | 36.6% |
| 28 | Hy4 preview· Epoch AI Benchmarking Hub data | 35% |
| 29 | Gemini 3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35% |
| 30 | Gemini 3.8 Flashall-pass rate · self-computed· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 35% |
| 31 | Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34.6% |
| 32 | Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34% |
| 33 | Gemini 3.7 Flashself-computed· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 34% |
| 34 | Muse Wonder Full· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 33.2% |
| 35 | Mistral Large 4high· Epoch AI Benchmarking Hub data | 32.8% |
| 36 | GPT-6.1 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 32% |
| 37 | Muse Wonder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30.8% |
| 38 | Muse Wonder 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30.8% |
| 39 | GPT-5.6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 30.7% |
| 40 | GPT-5.6 SolOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 30.7% |
| 41 | Claude Fable 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 29.8% |
| 42 | Claude Fable 5Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29.8% |
| 43 | Claude Fable 5OpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29.8% |
| 44 | GPT 5.5OpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 26% |
| 45 | GPT 5.5Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 24.9% |
| 46 | GPT-5.6 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 24.7% |
| 47 | GPT-5.6 TerraOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 24.7% |
| 48 | GPT-5.6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 22.7% |
| 49 | GPT-5.6 LunaOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 22.7% |
| 50 | Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 22.5% |
Showing 1–50 of 55 results.
Data credits: 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. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence)