Compare · ModelsLive · 2 picked · head to head
Claude Opus 4.1 vs Gemini 1.5 Pro (Feb 2024)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Opus 4.1 wins on 5/5 benchmarks
Claude Opus 4.1 wins 5 of 5 shared benchmarks. Leads in coding · knowledge · math.
Category leads
coding·Claude Opus 4.1knowledge·Claude Opus 4.1math·Claude Opus 4.1reasoning·Claude Opus 4.1
Hype vs Reality
Attention vs performance
Claude Opus 4.1
#137 by perf·no signal
Gemini 1.5 Pro (Feb 2024)
#138 by perf·no signal
Best value
Claude Opus 4.1
Claude Opus 4.1
0.9 pts/$
$45.00/M
Gemini 1.5 Pro (Feb 2024)
—
no price
Vendor risk
Who is behind the model
Anthropic
$380.0B·Tier 1
Google DeepMind
$4.00T·Tier 1
Head to head
5 benchmarks · 2 models
Claude Opus 4.1Gemini 1.5 Pro (Feb 2024)
Cybench
Claude Opus 4.1 leads by +34.5
Cybench · evaluates AI on real Capture-The-Flag cybersecurity challenges, testing vulnerability analysis, exploitation, and security reasoning.
Claude Opus 4.1
42.0
Gemini 1.5 Pro (Feb 2024)
7.5
GPQA diamond
Claude Opus 4.1 leads by +41.9
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Opus 4.1
69.7
Gemini 1.5 Pro (Feb 2024)
27.8
OTIS Mock AIME 2024-2025
Claude Opus 4.1 leads by +62.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 4.1
68.9
Gemini 1.5 Pro (Feb 2024)
6.7
SimpleBench
Claude Opus 4.1 leads by +39.5
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Opus 4.1
52.0
Gemini 1.5 Pro (Feb 2024)
12.5
WeirdML
Claude Opus 4.1 leads by +20.6
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Opus 4.1
42.8
Gemini 1.5 Pro (Feb 2024)
22.2
Full benchmark table
| Benchmark | Claude Opus 4.1 | Gemini 1.5 Pro (Feb 2024) |
|---|---|---|
Cybench Cybench · evaluates AI on real Capture-The-Flag cybersecurity challenges, testing vulnerability analysis, exploitation, and security reasoning. | 42.0 | 7.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 69.7 | 27.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 68.9 | 6.7 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 52.0 | 12.5 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 42.8 | 22.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $15.00 | $75.00 | 200K tokens (~100 books) | $300.00 | |
| — | — | — | — |