Claude Opus 5.5 vs Gemini 4 Argon
Different efforts: medium · high · Compare all at high
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
Opus 5.554.7
Gemini 4 Argon57.1
Arena Text · overall Arena Text · overall: Human pairwise preferences in the stated text vote pool
Opus 5.5 · high1,508
Gemini 4 Argon1,524
Arena Text · Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool
Opus 5.5 · high1,583.6
Gemini 4 Argon1,608.3
Arena Text · English Arena Text · english: Human pairwise preferences in the stated text vote pool
Opus 5.5 · high1,516.9
Gemini 4 Argon1,537.7
Arena Text · instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool
Opus 5.5 · high1,535.8
Gemini 4 Argon1,535.6
Arena Text · non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool
Opus 5.5 · high1,506.9
Gemini 4 Argon1,521.7
Arena Text · Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool
Opus 5.5 · high1,519.1
Gemini 4 Argon1,534
Arena Text · Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool
Opus 5.5 · high1,519
Gemini 4 Argon1,504.4
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty
Opus 5.540.3
Gemini 4 Argon42.4
SimpleQA Verified v1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access
Opus 5.5 · max72.2
Gemini 4 Argon76
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps
Opus 5.527.7
Gemini 4 Argon27.1
AA Intelligence Index 4.3.2 AA Intelligence Index 4.3.2: Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score
Opus 5.551.2
Gemini 4 Argon52.6
AA Omniscience · Accuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test
Opus 5.564.6
Gemini 4 Argon49.9
AA Omniscience · Hallucination Rate AA Omniscience · Hallucination Rate: Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test · lower is better
Opus 5.568.4
Gemini 4 Argon15.1
AA-LCR (long context) 1.1 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens)
Opus 5.584.3
Gemini 4 Argon79.7
GDP.pdf · AA all-pass GDP.pdf · AA all-pass: Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes
Opus 5.525.6
Gemini 4 Argon21.8
ARC-AGI-1 · public evaluation ARC-AGI-1 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit
Opus 5.598.3
Gemini 4 Argon99.5
ARC-AGI-1 · semi-private ARC-AGI-1 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit
Opus 5.597.5
Gemini 4 Argon98.5
ARC-AGI-2 · public evaluation ARC-AGI-2 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit
Opus 5.593.5
Gemini 4 Argon97.1
ARC-AGI-2 · semi-private ARC-AGI-2 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit
Opus 5.587.5
Gemini 4 Argon91.3
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position
Opus 5.5 · max67
Gemini 4 Argon59
FrontierMath Tier 4 (v2) FrontierMath Tier 4 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition
Opus 5.5 · max95
Gemini 4 Argon78
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition
Opus 5.5 · max91.2
Gemini 4 Argon86
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game
Opus 5.5 · max71
Gemini 4 Argon64
MathArena · ArXivMath · August 2026 MathArena · arxiv · 08/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high86
Gemini 4 Argon82.5
MathArena · ArXivMath · September 2026 MathArena · arxiv · 09/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high82.1
Gemini 4 Argon87.7
MathArena · BrokenArXiv · August 2026 MathArena · arxiv_false · 08/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high77.4
Gemini 4 Argon54.2
MathArena · BrokenArXiv · September 2026 MathArena · arxiv_false · 09/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high76.7
Gemini 4 Argon49.7
MathArena · ArXivLean · September 2026 MathArena · arxivlean · 09/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high47.2
Gemini 4 Argon39.6
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters
Opus 5.549.8
Gemini 4 Argon58.8
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts
Opus 5.591.4
Gemini 4 Argon87.4
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass
Opus 5.550.5
Gemini 4 Argon54.8
Vals Science Index Vals Science Index: Scientific problem solving across the index’s component evaluations
Opus 5.558.7
Gemini 4 Argon55.4
Arena Text · French Arena Text · french: Human pairwise preferences in the stated text vote pool
Opus 5.5 · high1,505.3
Gemini 4 Argon—
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete
Opus 5.5 · max66.7
Gemini 4 Argon—
ARC-AGI-3 · semi-private ARC-AGI-3 · semi-private: Measures interactive game solving through relative human action efficiency
Opus 5.5—
Gemini 4 Argon · low49.8
FrontierMath Erdos FrontierMath Erdos: Models solve expert-written advanced mathematics problems on the named tier and edition
Opus 5.5 · max2.9
Gemini 4 Argon—
MathArena · ArXivMath · June 2026 MathArena · arxiv · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high83.3
Gemini 4 Argon—
MathArena · ArXivMath · May 2026 MathArena · arxiv · 05/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high81.7
Gemini 4 Argon—
MathArena · BrokenArXiv · June 2026 MathArena · arxiv_false · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high100
Gemini 4 Argon—
MathArena · BrokenArXiv · May 2026 MathArena · arxiv_false · 05/2026: Answer accuracy on the named mathematics competition under the recorded effort
Opus 5.5 · high95
Gemini 4 Argon—
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench
Opus 5.5—
Gemini 4 Argon88.3
| Benchmark | Opus 5.5 | Gemini 4 Argon |
|---|---|---|
| Humanity's Last Exam | 54.7 | 57.1 |
| Arena Text · overall | 1,508 · high | 1,524 |
| Arena Text · Chinese | 1,583.6 · high | 1,608.3 |
| Arena Text · English | 1,516.9 · high | 1,537.7 |
| Arena Text · instruction following | 1,535.8 · high | 1,535.6 |
| Arena Text · non-English | 1,506.9 · high | 1,521.7 |
| Arena Text · Russian | 1,519.1 · high | 1,534 |
| Arena Text · Spanish | 1,519 · high | 1,504.4 |
| AA Omniscience Index | 40.3 | 42.4 |
| SimpleQA Verified v1 | 72.2 · max | 76 |
| CritPt (physics) | 27.7 | 27.1 |
| AA Intelligence Index 4.3.2 | 51.2 | 52.6 |
| AA Omniscience · Accuracy | 64.6 | 49.9 |
| AA Omniscience · Hallucination Rate | 68.4 | 15.1 |
| AA-LCR (long context) 1.1 | 84.3 | 79.7 |
| GDP.pdf · AA all-pass | 25.6 | 21.8 |
| ARC-AGI-1 · public evaluation | 98.3 | 99.5 |
| ARC-AGI-1 · semi-private | 97.5 | 98.5 |
| ARC-AGI-2 · public evaluation | 93.5 | 97.1 |
| ARC-AGI-2 · semi-private | 87.5 | 91.3 |
| Chess Puzzles | 67 · max | 59 |
| FrontierMath Tier 4 (v2) | 95 · max | 78 |
| FrontierMath Tiers 1–3 (v2) | 91.2 · max | 86 |
| Mystery Game Puzzles | 71 · max | 64 |
| MathArena · ArXivMath · August 2026 | 86 · high | 82.5 |
| MathArena · ArXivMath · September 2026 | 82.1 · high | 87.7 |
| MathArena · BrokenArXiv · August 2026 | 77.4 · high | 54.2 |
| MathArena · BrokenArXiv · September 2026 | 76.7 · high | 49.7 |
| MathArena · ArXivLean · September 2026 | 47.2 · high | 39.6 |
| Vals MedCode | 49.8 | 58.8 |
| Vals MedScribe | 91.4 | 87.4 |
| Vals Legal Research Bench | 50.5 | 54.8 |
| Vals Science Index | 58.7 | 55.4 |
| Arena Text · French | 1,505.3 · high | — |
| MLCR-AA | 66.7 · max | — |
| ARC-AGI-3 · semi-private | — | 49.8 · low |
| FrontierMath Erdos | 2.9 · max | — |
| MathArena · ArXivMath · June 2026 | 83.3 · high | — |
| MathArena · ArXivMath · May 2026 | 81.7 · high | — |
| MathArena · BrokenArXiv · June 2026 | 100 · high | — |
| MathArena · BrokenArXiv · May 2026 | 95 · high | — |
| Vals LegalBench | — | 88.3 |
Specs
| Spec | Opus 5.5 | Gemini 4 Argon |
|---|---|---|
| Input, per 1M | $4 | !$2 |
| Output, per 1M | $20 | !$10 |
| Cost per task? | $1.34 | $1.99 |
| Speed, tok/s | 81 | 84 |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | Sep 2026 | Oct 2026 |
| See images | ✓ | ✓ |
| Read PDFs | ✓ | ✓ |
| Hear audio | — | ✓ |
| Watch video | — | ✓ |
| Call tools | ✓ | ✓ |
| Force a tool call | — | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ✓ | ✓ |
| Run code | ✓ | ✓ |
| Use a computer | ✓ | ? |
What breaks when you switch
Opus 5.5 → 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 5.5
No forced tool use›
Forced tool_choice any or tool returns HTTP 400; remove the forced choice.
Thinking is always on›
Disabled thinking or a manual budget returns HTTP 400; omit thinking or use adaptive thinking.
Remove sampling parameters›
Non-default temperature, top_p or top_k returns HTTP 400; omit these parameters and use prompting.
No assistant prefill›
Assistant prefill returns HTTP 400; use structured outputs or system instructions, with system instructions on Bedrock.
Old computer tool rejected · Claude API / Google Cloud›
The computer_20251124 tool returns HTTP 400 on the Claude API and Google Cloud; use computer_toolset_20260801 there.
Return thinking blocks unmodified›
Edited, reordered or partially dropped thinking blocks return HTTP 400; echo assistant messages complete and unmodified with tool results.