Benchmark
Artificial Analysis Intelligence Index
Scores are index points out of 100. Higher is better.
Benchmark sourceScores from OpenRouter data docs, BenchBoard docs.
- Models measured
- 72
- Scores recorded
- 92
- Sources
- 2
- IQ weight
- No weight published
Score distribution
- 37
- Mean
- 36.6
- Median
- 18.7
- Std dev
- 6.3
- 10th percentile
- 59.9
- 90th percentile
- 3.8
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 51 | Inkling Small· OpenRouter data docs | 12.9 |
| 52 | Inkling FP4· OpenRouter data docs | 12.5 |
| 53 | Nemotron 3 Ultra· OpenRouter data docs | 11.8 |
| 54 | Gemini 3.5 Flash Lite· OpenRouter data docs | 11.7 |
| 55 | Claude Haiku 4.5· OpenRouter data docs | 7.4 |
| 56 | Muse Glimmer 30B· OpenRouter data docs | 6.3 |
| 57 | Command A Plus· OpenRouter data docs | 6.2 |
| 58 | Gemini 3.1 Flash Lite· OpenRouter data docs | 6.2 |
| 59 | LFM3 1.7B· OpenRouter data docs | 6 |
| 60 | Nemotron 3.5 Lightning· OpenRouter data docs | 5.5 |
| 61 | Granite 4.2 8B· OpenRouter data docs | 5.1 |
| 62 | Mistral Medium 3.5· OpenRouter data docs | 4.6 |
| 63 | Gemma 4 31B IT· OpenRouter data docs | 4.4 |
| 64 | Mistral Small2603· OpenRouter data docs | 4.3 |
| 65 | GPT OSS 120B· OpenRouter data docs | 3.8 |
Showing 51–65 of 65 results.
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model | Score |
|---|---|
| Claude Fable 5Artificial Analysis Intelligence Index v4.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.9 |
| Claude Fable 5Artificial Analysis Intelligence Index v4.1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.1 |
| Claude Fable 5v4.3 · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50 |
| Claude Fable 5.1Artificial Analysis Intelligence Index v4.1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65.7 |
| Claude Fable 5.1v4.3 · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53 |
| Claude Fable 5.1v4.3 · x-high effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53 |
| Claude Opus 4.8Artificial Analysis Intelligence Index v4.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.7 |
| Claude Opus 5Artificial Analysis Intelligence Index v4.1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 63.1 |
| Claude Opus 5v4.3 · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51 |
| Gemini 3.1 Pro PreviewArtificial Analysis Intelligence Index v4.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 46.5 |
| Gemini 3.5 FlashArtificial Analysis Intelligence Index v4.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.2 |
| Gemini 3.7 FlashAugust 2026 snapshot· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56 |
| Gemini 3.8 FlashArtificial Analysis Intelligence Index v4.1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 58.7 |
| Gemini 3.8 Flashv4.3 · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 41 |
| GLM 5.3 Flashv4.1.1 / $0.045 per task(折后)· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57 |
| GPT 5.5Artificial Analysis Intelligence Index v4.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 54.8 |
| GPT-5.6 LunaArtificial Analysis Intelligence Index v4.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.2 |
| GPT-5.6 SolArtificial Analysis Intelligence Index v4.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 58.9 |
| GPT-5.6 SolArtificial Analysis Intelligence Index v4.1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.9 |
| GPT-5.6 Solv4.3 · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 47 |
| GPT-5.6 TerraArtificial Analysis Intelligence Index v4.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55 |
| GPT-6 AstraArtificial Analysis Intelligence Index v4.1.1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 61.2 |
| GPT-6 Astrav4.3 · high effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51 |
| GPT-6 Astrav4.3 · low effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 46 |
| GPT-6 Astrav4.3 · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53 |
| GPT-6 Astrav4.3 · medium effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50 |
| GPT-6 Astrav4.3 · x-high effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53 |