TestsBenchmarks · Reasoning
Vals Index
Vals.ai composite of real-world task benchmarks (finance, legal, coding, etc.).
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon | Google (Gemini / DeepMind) | 68.9% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 2 | Claude Sonnet 5.5 | Anthropic | 67.0% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 3 | Claude Opus 5.5 | Anthropic | 67.0% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 4 | Claude Fable 5.1 | Anthropic | 65.8% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 5 | Claude Opus 5 | Anthropic | 63.7% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 6 | GPT-6 Astra | OpenAI | 63.1% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 7 | Claude Fable 5 | Anthropic | 61.4% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 8 | GPT-6.1 Sol | OpenAI | 61.1% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 9 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 58.2% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 10 | GPT-5.6 Sol | OpenAI | 58.0% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 11 | GPT-6 Sol | OpenAI | 57.5% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 12 | MiMo-V2.6-Pro | Xiaomi MiMo | 55.2% | Default | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 13 | Claude Opus 4.8 | Anthropic | 55.1% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 14 | Grok 4.7 | SpaceXAI (formerly xAI) | 55.0% | Extra highreasoning_effort=xhigh | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 15 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 54.8% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 16 | GLM-5.3 | Z.ai (Zhipu) | 53.5% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 17 | MiMo-V2.6-Flash | Xiaomi MiMo | 53.2% | Default | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 18 | GPT-5.6 Terra | OpenAI | 53.1% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 19 | Grok 4.6 | SpaceXAI (formerly xAI) | 52.1% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 20 | Claude Sonnet 5 | Anthropic | 51.8% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 21 | GPT-5.6 Luna | OpenAI | 51.7% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 22 | DeepSeek V4.1 Flash | DeepSeek | 51.3% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 23 | Gemini 3.7 Flash | Google (Gemini / DeepMind) | 51.3% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |
| 24 | GPT-6 Luna | OpenAI | 51.2% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 30 Sep 2026 |