Claude Opus 4.6 vs Gemini 4 Argon
Vals Science Index?
Opus 4.6—
Gemini 4 Argon55.4
| Benchmark | Opus 4.6 | Gemini 4 Argon |
|---|---|---|
| Humanity's Last Exam | 19.1 | 57.1 |
| Arena Text · overall | 1,503 | 1,524 |
| Arena Text · Chinese | 1,551 | 1,600.2 |
| Arena Text · English | 1,511.3 | 1,525.8 |
| Arena Text · French | 1,511.9 | 1,543.2 |
| Arena Text · instruction following | 1,521 | 1,527.6 |
| Arena Text · non-English | 1,487.6 | 1,518.9 |
| Arena Text · Polish | 1,497.2 | 1,530 |
| Arena Text · Russian | 1,495.3 | 1,536.8 |
| Arena Text · Spanish | 1,503.5 | 1,507.6 |
| AA Omniscience Index | 2.4 | 42.4 |
| SimpleQA Verified v1 | 47 · max | 76 |
| CritPt (physics) | 2.8 | 27.1 |
| AA Intelligence Index 4.3.2 | 26.4 | 52.6 |
| AA Omniscience · Accuracy | 45.8 | 49.9 |
| AA Omniscience · Hallucination Rate | 80.1 | 15.1 |
| AA-LCR (long context) 1.1 | 67 | 79.7 |
| ARC-AGI-1 · public evaluation | 96.3 | 99.5 |
| ARC-AGI-1 · semi-private | 94 | 98.5 |
| ARC-AGI-2 · public evaluation | 79 | 97.1 |
| ARC-AGI-2 · semi-private | 69.2 | 91.3 |
| Chess Puzzles | 21 · max | 59 |
| FrontierMath Tier 4 (v2) | 26.8 · max | 78 |
| FrontierMath Tiers 1–3 (v2) | 66 · max | 86 |
| Mystery Game Puzzles | 25 · max | 64 |
| Vals LegalBench | 85.3 | 88.3 |
| Vals MedCode | 49.1 | 58.8 |
| Vals MedScribe | 86.1 | 87.4 |
| Arena Text · German | 1,501.9 | — |
| Arena Text · Japanese | 1,488 | — |
| Arena Text · Korean | 1,448.8 | — |
| GDP.pdf · AA all-pass | — | 21.8 |
| IFBench (instructions) | 44.6 | — |
| MLCR-AA | — | 13.9 |
| ARC-AGI-3 · semi-private | — | 49.8 · low |
| EQ-Bench 3 | 1,712.4 | — |
| FrontierMath | 40.7 · max | — |
| FrontierMath Tier 4 | 22.9 · max | — |
| MathArena · Apex | 34.5 | — |
| MathArena · Apex Shortlist | 86.7 | — |
| MathArena · ArXivMath · August 2026 | — | 82.5 |
| MathArena · ArXivMath · December 2025 | 57.4 | — |
| MathArena · ArXivMath · February 2026 | 40.6 | — |
| MathArena · ArXivMath · January 2026 | 72.8 | — |
| MathArena · ArXivMath · March 2026 | 62.5 | — |
| MathArena · ArXivMath · September 2026 | — | 87.7 |
| MathArena · BrokenArXiv · August 2026 | — | 54.2 |
| MathArena · BrokenArXiv · February 2026 | 3.2 | — |
| MathArena · BrokenArXiv · March 2026 | 5.8 | — |
| MathArena · BrokenArXiv · September 2026 | — | 49.7 |
| MathArena · ArXivLean · September 2026 | — | 39.6 |
| MathArena · Project Euler | 87.7 | — |
| MathArena · Kangaroo 2025 1-2 | 59.4 | — |
| MathArena · Kangaroo 2025 11-12 | 87.5 | — |
| MathArena · Kangaroo 2025 3-4 | 50 | — |
| MathArena · Kangaroo 2025 5-6 | 58.3 | — |
| MathArena · Kangaroo 2025 7-8 | 86.7 | — |
| MathArena · Kangaroo 2025 9-10 | 91.7 | — |
| MathArena · USAMO 2026 | 47 | — |
| Vals Legal Research Bench | — | 54.8 |
| Vals Science Index | — | 55.4 |
Specs
| Spec | Opus 4.6 | Gemini 4 Argon |
|---|---|---|
| Input, per 1M | $5 | !$2 |
| Output, per 1M | $25 | !$10 |
| Cost per task? | — | $1.62 |
| Speed, tok/s | 43 | 79 |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | Feb 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 4.6 → 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 4.6
Nothing known.