Compare · ModelsLive · 2 picked · head to head
Claude Opus 4.6 vs Gemini 3.5 Flash
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Opus 4.6 wins on 12/21 benchmarks
Claude Opus 4.6 wins 12 of 21 shared benchmarks. Leads in agentic · arena · general.
Category leads
agentic·Claude Opus 4.6reasoning·Gemini 3.5 Flasharena·Claude Opus 4.6knowledge·Gemini 3.5 Flashgeneral·Claude Opus 4.6math·Claude Opus 4.6coding·Gemini 3.5 Flash
Hype vs Reality
Attention vs performance
Claude Opus 4.6
#136 by perf·#9 by attention
Gemini 3.5 Flash
#82 by perf·#5 by attention
Best value
Gemini 3.5 Flash
3.2x better value than Claude Opus 4.6
Claude Opus 4.6
3.2 pts/$
$15.00/M
Gemini 3.5 Flash
10.4 pts/$
$5.25/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Google DeepMind
$4.20T·Tier 1
Head to head
21 benchmarks · 2 models
Claude Opus 4.6Gemini 3.5 Flash
APEX-Agents
Claude Opus 4.6 leads by +18.8
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Opus 4.6
46.3
Gemini 3.5 Flash
27.5
ARC-AGI
Claude Opus 4.6 leads by +1.5
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Opus 4.6
94.0
Gemini 3.5 Flash
92.5
ARC-AGI-2
Gemini 3.5 Flash leads by +2.9
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Opus 4.6
69.2
Gemini 3.5 Flash
72.1
Chatbot Arena Elo · Coding
Claude Opus 4.6 leads by +31.5
Claude Opus 4.6
1537.0
Gemini 3.5 Flash
1505.5
Chatbot Arena Elo · Overall
Claude Opus 4.6 leads by +21.0
Claude Opus 4.6
1497.3
Gemini 3.5 Flash
1476.3
Chess Puzzles
Gemini 3.5 Flash leads by +34.7
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Opus 4.6
12.7
Gemini 3.5 Flash
47.4
Dtbench
Gemini 3.5 Flash leads by +5.8
Claude Opus 4.6
85.3
Gemini 3.5 Flash
91.1
Ebr Bench
Claude Opus 4.6 leads by +7.9
Claude Opus 4.6
12.7
Gemini 3.5 Flash
4.8
FrontierMath-2025-02-28-Private
Claude Opus 4.6 leads by +1.7
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Claude Opus 4.6
40.7
Gemini 3.5 Flash
39.0
FrontierMath-Tier-4-2025-07-01-Private
Claude Opus 4.6 leads by +8.3
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
Claude Opus 4.6
22.9
Gemini 3.5 Flash
14.6
FrontierMath-Tier-4-v2-Private
Claude Opus 4.6
26.8
Gemini 3.5 Flash
26.8
FrontierMath-Tiers-1-3-v2-Private
Claude Opus 4.6 leads by +3.1
Claude Opus 4.6
66.0
Gemini 3.5 Flash
62.8
GPQA diamond
Gemini 3.5 Flash leads by +3.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Opus 4.6
87.4
Gemini 3.5 Flash
90.4
Lmca
Claude Opus 4.6 leads by +10.1
Claude Opus 4.6
65.6
Gemini 3.5 Flash
55.5
Mystery Game Puzzles
Gemini 3.5 Flash leads by +7.7
Claude Opus 4.6
17.4
Gemini 3.5 Flash
25.1
OTIS Mock AIME 2024-2025
Gemini 3.5 Flash leads by +1.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 4.6
94.4
Gemini 3.5 Flash
95.5
Proofbench
Claude Opus 4.6 leads by +19.0
Claude Opus 4.6
50.0
Gemini 3.5 Flash
31.0
SimpleBench
Gemini 3.5 Flash leads by +10.9
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Opus 4.6
61.1
Gemini 3.5 Flash
72.0
SimpleQA Verified
Gemini 3.5 Flash leads by +19.2
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Opus 4.6
47.0
Gemini 3.5 Flash
66.2
SWE-Bench verified
Gemini 3.5 Flash leads by +0.6
SWE-bench Verified · 500 human-validated tasks from 12 real Python repositories (Django, Flask, scikit-learn, sympy, and others). Each task requires the model to produce a git patch that resolves a real GitHub issue and passes the test suite. The verified subset eliminates ambiguous tasks from the original SWE-bench. Claude Mythos Preview leads at 93.9%, crossing 90% for the first time in 2026. Opus 4.6 scores 80.8%. The benchmark remains the most-cited evaluation for code-generation capability.
Claude Opus 4.6
78.7
Gemini 3.5 Flash
79.3
WeirdML
Claude Opus 4.6 leads by +15.3
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Opus 4.6
78.0
Gemini 3.5 Flash
62.6
Full benchmark table
| Benchmark | Claude Opus 4.6 | Gemini 3.5 Flash |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 46.3 | 27.5 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 94.0 | 92.5 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 69.2 | 72.1 |
Chatbot Arena Elo · Coding | 1537.0 | 1505.5 |
Chatbot Arena Elo · Overall | 1497.3 | 1476.3 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 12.7 | 47.4 |
Dtbench | 85.3 | 91.1 |
Ebr Bench | 12.7 | 4.8 |
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 40.7 | 39.0 |
FrontierMath-Tier-4-2025-07-01-Private FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning. | 22.9 | 14.6 |
FrontierMath-Tier-4-v2-Private | 26.8 | 26.8 |
FrontierMath-Tiers-1-3-v2-Private | 66.0 | 62.8 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.4 | 90.4 |
Lmca | 65.6 | 55.5 |
Mystery Game Puzzles | 17.4 | 25.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 94.4 | 95.5 |
Proofbench | 50.0 | 31.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 61.1 | 72.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 47.0 | 66.2 |
SWE-Bench verified SWE-bench Verified · 500 human-validated tasks from 12 real Python repositories (Django, Flask, scikit-learn, sympy, and others). Each task requires the model to produce a git patch that resolves a real GitHub issue and passes the test suite. The verified subset eliminates ambiguous tasks from the original SWE-bench. Claude Mythos Preview leads at 93.9%, crossing 90% for the first time in 2026. Opus 4.6 scores 80.8%. The benchmark remains the most-cited evaluation for code-generation capability. | 78.7 | 79.3 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 78.0 | 62.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $5.00 | $25.00 | 1.0M tokens (~500 books) | $100.00 | |
| $1.50 | $9.00 | 1.0M tokens (~524 books) | $33.75 |