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 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
Claude Opus 4.1
#137 by perf·no signal
QUIET
Gemini 1.5 Pro (Feb 2024)
#138 by perf·no signal
QUIET
Best value
Claude Opus 4.1
0.9 pts/$
$45.00/M
Gemini 1.5 Pro (Feb 2024)
no price
Vendor risk
Anthropic logo
Anthropic
$380.0B·Tier 1
Medium risk
Google DeepMind logo
Google DeepMind
$4.00T·Tier 1
Low risk
Head to head
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
BenchmarkClaude Opus 4.1Gemini 1.5 Pro (Feb 2024)
Cybench
Cybench · evaluates AI on real Capture-The-Flag cybersecurity challenges, testing vulnerability analysis, exploitation, and security reasoning.
42.07.5
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
69.727.8
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
68.96.7
SimpleBench
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
52.012.5
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
42.822.2
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Anthropic logoClaude Opus 4.1$15.00$75.00200K tokens (~100 books)$300.00
Google DeepMind logoGemini 1.5 Pro (Feb 2024)