Claude Opus 5 vs Gemini 4 Argon
Vals Science Index?
Opus 547.9
Gemini 4 Argon55.4
| Benchmark | Opus 5 | Gemini 4 Argon |
|---|---|---|
| Humanity's Last Exam | 51.3 | 57.1 |
| Arena Text · overall | 1,490 · max | 1,524 |
| Arena Text · Chinese | 1,573.4 · max | 1,608.3 |
| Arena Text · English | 1,507.3 · max | 1,537.7 |
| Arena Text · instruction following | 1,517.8 · max | 1,535.6 |
| Arena Text · non-English | 1,500.5 · max | 1,521.7 |
| Arena Text · Russian | 1,507.2 · max | 1,534 |
| Arena Text · Spanish | 1,519.5 · max | 1,504.4 |
| AA Omniscience Index | 31 | 42.4 |
| SimpleQA Verified v1 | 63.3 | 76 |
| CritPt (physics) | 26.9 | 27.1 |
| AA Intelligence Index 4.3.2 | 44.8 | 52.6 |
| AA Omniscience · Accuracy | 57.1 | 49.9 |
| AA Omniscience · Hallucination Rate | 60.7 | 15.1 |
| AA-LCR (long context) 1.1 | 82 | 79.7 |
| GDP.pdf · AA all-pass | 20 | 21.8 |
| ARC-AGI-1 · public evaluation | 99 · max | 99.5 |
| ARC-AGI-1 · semi-private | 97.5 · max | 98.5 |
| ARC-AGI-2 · public evaluation | 97.1 · max | 97.1 |
| ARC-AGI-2 · semi-private | 90.4 · max | 91.3 |
| ARC-AGI-3 · semi-private | 30.2 · high | 49.8 · low |
| Chess Puzzles | 43 · max | 59 |
| FrontierMath Tier 4 (v2) | 73.2 · max | 78 |
| FrontierMath Tiers 1–3 (v2) | 85.6 · max | 86 |
| Mystery Game Puzzles | 59 · max | 64 |
| Vals LegalBench | 87 | 88.3 |
| Vals MedCode | 63.6 | 58.8 |
| Vals MedScribe | 91 | 87.4 |
| Vals Legal Research Bench | 55.3 | 54.8 |
| Vals Science Index | 47.9 | 55.4 |
| Arena Text · French | 1,519.5 · high | — |
| Arena Text · German | 1,525.9 · max | — |
| Arena Text · Japanese | 1,515.4 · max | — |
| Arena Text · Korean | 1,520.7 · max | — |
| Arena Text · Polish | 1,519.9 · max | — |
| MLCR-AA | 56.1 | — |
| FrontierMath Erdos | 0 · max | — |
| MathArena · ArXivMath · August 2026 | — | 82.5 |
| MathArena · ArXivMath · June 2026 | 82.6 · max | — |
| MathArena · ArXivMath · September 2026 | — | 87.7 |
| MathArena · BrokenArXiv · August 2026 | — | 54.2 |
| MathArena · BrokenArXiv · June 2026 | 90.7 · max | — |
| MathArena · BrokenArXiv · September 2026 | — | 49.7 |
| MathArena · ArXivLean · June 2026 | 32.6 · max | — |
| MathArena · ArXivLean · September 2026 | — | 39.6 |
Specs
| Spec | Opus 5 | Gemini 4 Argon |
|---|---|---|
| Input, per 1M | $5 | !$2 |
| Output, per 1M | $25 | !$10 |
| Cost per task? | $2.19 | $1.99 |
| Speed, tok/s | 55 | 84 |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | Jul 2026 | Oct 2026 |
| See images | ✓ | ✓ |
| Read PDFs | 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 → Gemini 4 Argon
Synchronous output stops at 65,536›
With background false, output limits above 65,536 tokens return HTTP 400; stay at or below that limit.
Sampling parameters are ignored›
temperature, top_p and top_k are ignored; remove them from requests.
No explicit caching›
Explicit caching is unavailable; omit explicit cache requests.
Gemini 4 Argon → Opus 5
Nothing known.