Benchmark
GDPval-AA v2
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are Elo ratings. Higher ratings are better.
- Models and systems measured
- 36
- Scores recorded
- 82
- Sources
- 1
- IQ weight
- 2.72
Score distribution
- 1,587.2
- Mean
- 1,631
- Median
- 253.9
- Std dev
- 1,314
- 10th percentile
- 1,844
- 90th percentile
- 735
- Min
This benchmark has a weight of 2.72 for chat models, measured over 34 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | 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. | 1,932 |
| 2 | 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. | 1,890 |
| 3 | Claude Opus 4.8Opus 4.8 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. | 1,890 |
| 4 | Claude Opus 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,861 |
| 5 | Claude Fable 5.1Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,853 |
| 6 | Claude Fable 5.1System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,853 |
| 7 | Claude Opus 5max· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,852 |
| 8 | Claude Opus 5.5Opus 5.5 System Card capability section · Artificial Analysis · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,846 |
| 9 | Claude Sonnet 5.5Artificial Analysis · max· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,844 |
| 10 | Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Artificial Analysis · Haiku 5.5 card snapshot · max· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,840 |
| 11 | Claude Opus 5Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,824 |
| 12 | Claude Opus 5Google Model Card· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,824 |
| 13 | Claude Opus 5max · Artificial Analysis Stirrup · 220 tasks · shell + web browsing · human baseline 1000· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,824 |
| 14 | Claude Opus 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,824 |
| 15 | Claude Opus 5.5Opus 5.5 System Card capability section · Artificial Analysis · xhigh effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,820 |
| 16 | GLM 5.3 FlashArtificial Analysis / Z.ai转载· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,773 |
| 17 | GLM 5.3Artificial Analysis / Z.ai转载· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,769 |
| 18 | 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. | 1,769 |
| 19 | GPT 5.5Opus 4.8 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. | 1,769 |
| 20 | 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. | 1,759.6 |
| 21 | Muse Spark 1.3max · Artificial Analysis Stirrup · 220 tasks · shell + web browsing · human baseline 1000· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,754 |
| 22 | Claude Opus 4.7Opus 4.8 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. | 1,753 |
| 23 | 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. | 1,747.8 |
| 24 | Claude Fable 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,747 |
| 25 | Qwen3.8 MaxArtificial Analysis / Z.ai转载· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,739 |
| 26 | GPT-5.6 SolOpus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,736 |
| 27 | Claude Fable 5.1Opus 5.5 System Card capability section · Artificial Analysis · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,735 |
| 28 | GPT-5.6 SolArtificial Analysis / Z.ai转载· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,730 |
| 29 | Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · Artificial Analysis · xhigh· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,725 |
| 30 | Claude Fable 5Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,723 |
| 31 | Claude Fable 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,723 |
| 32 | GPT-5.6 SolAnthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,711 |
| 33 | GPT-5.6 SolSystem Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,711 |
| 34 | GPT-5.6 SolGoogle Model Card· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,710 |
| 35 | GPT-5.6 Solmax · Artificial Analysis Stirrup · 220 tasks · shell + web browsing · human baseline 1000· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,710 |
| 36 | Claude Opus 5Opus 5.5 System Card capability section · Artificial Analysis · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,708 |
| 37 | Grok 4.7release-page snapshot· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,695 |
| 38 | Kimi K3snapshot 2026-07-23· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,686 |
| 39 | Kimi K3Artificial Analysis / Z.ai转载· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,682 |
| 40 | Hy4 previewofficial model-card appendix· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,678 |
| 41 | Muse Spark 1.2Meta 官方发布图· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,631 |
| 42 | Claude Haiku 5.5Artificial Analysis · max· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,620 |
| 43 | Claude Sonnet 5Artificial Analysis · as of 2026-06-17· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,618 |
| 44 | Muse Spark 1.2xhigh · Artificial Analysis Stirrup · 220 tasks · shell + web browsing · human baseline 1000· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,615 |
| 45 | Claude Sonnet 5Gemini 3.6 Flash Model Card · July 2026· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,607 |
| 46 | Claude Opus 4.8OpenAI 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. | 1,600.1 |
| 47 | Claude Opus 4.8max · Artificial Analysis leaderboard· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,600 |
| 48 | Claude Opus 4.8Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,593 |
| 49 | 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. | 1,593 |
| 50 | 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. | 1,591.8 |
Showing 1–50 of 80 results.
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| GPT-6 Sol (Sonnet 5.5 table label)source table label · max effort· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,487 |
| Muse Spark (version unspecified)Meta Model API · highest effort · version unspecified · Artificial Analysis leaderboard· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 1,145 |