Claude Opus 5 vs GPT-6.1 Sol
Vals Science Index?
Opus 547.9
GPT-6.1 Sol59.6
| Benchmark | Opus 5 | GPT-6.1 Sol |
|---|---|---|
| Humanity's Last Exam | 51.3 | 49.9 |
| Arena Text · overall | 1,490 · max | 1,484 · max |
| Arena Text · Chinese | 1,573.1 · max | 1,484.1 · max |
| Arena Text · English | 1,508.1 · max | 1,450.7 · max |
| Arena Text · French | 1,518.4 · high | 1,461.2 · max |
| Arena Text · instruction following | 1,518.4 · max | 1,466.9 · max |
| Arena Text · non-English | 1,501.3 · max | 1,434.7 · max |
| Arena Text · Russian | 1,507.9 · max | 1,458.3 · max |
| Arena Text · Spanish | 1,522 · max | 1,444.7 · max |
| AA Omniscience Index | 31 | 40 |
| SimpleQA Verified v1 | 63.3 | 73.9 · max |
| CritPt (physics) | 26.9 | 27.7 |
| AA Intelligence Index 4.3.2 | 44.8 | 47.8 |
| AA Omniscience · Accuracy | 57.1 | 60.4 |
| AA Omniscience · Hallucination Rate | 60.7 | 51.6 |
| AA-LCR (long context) 1.1 | 82 | 83.3 |
| GDP.pdf · AA all-pass | 20 | 30 |
| MLCR-AA | 13.9 | 32.2 |
| ARC-AGI-1 · public evaluation | 99 · max | 97.9 |
| ARC-AGI-1 · semi-private | 97.5 · max | 95.5 |
| ARC-AGI-2 · public evaluation | 97.1 · max | 90.6 |
| ARC-AGI-2 · semi-private | 90.4 · max | 86.7 |
| ARC-AGI-3 · semi-private | 30.2 · high | 10.6 |
| Chess Puzzles | 43 · max | 68 · max |
| FrontierMath Erdos | 0 · max | 4.4 · max |
| FrontierMath Tier 4 (v2) | 73.2 · max | 100 · max |
| FrontierMath Tiers 1–3 (v2) | 85.6 · max | 93.7 · max |
| Mystery Game Puzzles | 59 · max | 80 · max |
| MathArena · ArXivMath · June 2026 | 82.6 · max | 94.4 · max |
| MathArena · BrokenArXiv · June 2026 | 90.7 · max | 100 · max |
| Vals MedCode | 63.6 | 48.8 |
| Vals MedScribe | 91 | 86.5 |
| Vals Legal Research Bench | 55.3 | 38.5 |
| Vals Science Index | 47.9 | 59.6 |
| Arena Text · German | 1,530.1 · max | — |
| Arena Text · Japanese | 1,520.5 · max | — |
| Arena Text · Korean | 1,518.1 · max | — |
| Arena Text · Polish | 1,522.9 · max | — |
| MathArena · ArXivMath · August 2026 | — | 96.5 · max |
| MathArena · ArXivMath · May 2026 | — | 95 · max |
| MathArena · ArXivMath · September 2026 | — | 91.5 · max |
| MathArena · BrokenArXiv · August 2026 | — | 86.3 · max |
| MathArena · BrokenArXiv · May 2026 | — | 90 · max |
| MathArena · BrokenArXiv · September 2026 | — | 82.7 · max |
| MathArena · ArXivLean · June 2026 | 32.6 · max | — |
| MathArena · ArXivLean · September 2026 | — | 35.9 · max |
| Vals LegalBench | 87 | — |
Specs
| Spec | Opus 5 | GPT-6.1 Sol |
|---|---|---|
| Input, per 1M | $5 | $2 |
| Output, per 1M | $25 | $10 |
| Cost per task? | $2.19 | $0.21 |
| Speed, tok/s | 51 | 52 |
| Context | 1M | 1.05M |
| Weights | Closed | Closed |
| Released | Jul 2026 | Sep 2026 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | Partial |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ✓ |
| Run code | ? | ✓ |
| Use a computer | ? | ✓ |
What breaks when you switch
Opus 5 → GPT-6.1 Sol
Remove unsupported parameters›
With reasoning enabled, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses message.output_text.logprobs includes.
Responses API for tool calling · Chat Completions›
Use Responses for tools; Chat Completions supports this model without tool calling.
No none or minimal reasoning›
The none and minimal reasoning efforts are unsupported; choose low, medium, high, xhigh or max.
More than 272K input tokens›
Prompts above 272K input tokens charge 2× input and cache rates and 1.5× output rates for the entire request.
Cache writes billed at 1.25x›
Cache writes cost 1.25× the uncached input token rate.
Ultrafast prices 6x Standard›
Ultrafast mode costs 6× Standard token prices.
GPT-6.1 Sol → Opus 5