TestsBenchmarks · Coding
Vals Code Migration
How well an agent re-implements real programs in another language (CLI tools, COBOL to Java) with tests and code-quality checks.
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Claude Sonnet 5.5 | Anthropic | 69.8% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 2 | Gemini 4 Argon | Google (Gemini / DeepMind) | 68.2% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 3 | GPT-6 Astra | OpenAI | 67.7% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 4 | Claude Opus 5.5 | Anthropic | 66.7% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 5 | GPT-6.1 Sol | OpenAI | 65.1% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 6 | Claude Opus 5 | Anthropic | 57.5% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 7 | GPT-6 Sol | OpenAI | 57.2% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 8 | Claude Fable 5 | Anthropic | 55.1% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 9 | Claude Fable 5.1 | Anthropic | 54.6% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 10 | GPT-5.6 Sol | OpenAI | 52.9% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 11 | GPT-5.6 Terra | OpenAI | 47.8% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 12 | Hy4 preview | Tencent Hunyuan | 47.4% | Default | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 13 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 47.4% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 14 | Claude Opus 4.8 | Anthropic | 47.3% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 15 | DeepSeek V4.1 Flash | DeepSeek | 45.6% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 16 | GPT-5.5 | OpenAI | 45.2% | Extra highreasoning_effort=xhigh | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 17 | Grok 4.7 | SpaceXAI (formerly xAI) | 44.8% | Extra highreasoning_effort=xhigh | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 18 | Grok 4.6 | SpaceXAI (formerly xAI) | 44.6% | Highreasoning_effort=high | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 19 | GPT-5.6 Luna | OpenAI | 44.5% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 20 | Claude Sonnet 5 | Anthropic | 44.4% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 21 | GLM-5.3 | Z.ai (Zhipu) | 44.2% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 22 | Claude Opus 4.7 | Anthropic | 43.9% | Maxeffort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 23 | MiMo-V2.6-Pro | Xiaomi MiMo | 43.0% | Default | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 24 | GPT-6 Luna | OpenAI | 42.5% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |
| 25 | DeepSeek V4 Pro (0813) | DeepSeek | 41.5% | Maxreasoning_effort=max | Independent testIndependentVals.ai ↗ | — | 29 Sep 2026 |