Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 4 vs Gemini 2.0 Flash
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 4 wins on 10/12 benchmarks
Claude Sonnet 4 wins 10 of 12 shared benchmarks. Leads in coding · reasoning · math.
Category leads
coding·Claude Sonnet 4reasoning·Claude Sonnet 4knowledge·Gemini 2.0 Flashmath·Claude Sonnet 4agentic·Claude Sonnet 4
Hype vs Reality
Attention vs performance
Claude Sonnet 4
#157 by perf·#10 by attention
Gemini 2.0 Flash
#140 by perf·no signal
Best value
Gemini 2.0 Flash
38.0x better value than Claude Sonnet 4
Claude Sonnet 4
5.1 pts/$
$9.00/M
Gemini 2.0 Flash
192.0 pts/$
$0.25/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Google DeepMind
$4.20T·Tier 1
Head to head
12 benchmarks · 2 models
Claude Sonnet 4Gemini 2.0 Flash
Aider polyglot
Claude Sonnet 4 leads by +23.1
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
Claude Sonnet 4
61.3
Gemini 2.0 Flash
38.2
ARC-AGI-2
Claude Sonnet 4 leads by +4.6
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Sonnet 4
5.9
Gemini 2.0 Flash
1.3
Fiction.LiveBench
Gemini 2.0 Flash leads by +14.2
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
Claude Sonnet 4
46.9
Gemini 2.0 Flash
61.1
FrontierMath-2025-02-28-Private
Claude Sonnet 4 leads by +5.5
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Claude Sonnet 4
7.3
Gemini 2.0 Flash
1.7
GeoBench
Gemini 2.0 Flash leads by +40.0
GeoBench · tests geographic knowledge and spatial reasoning across countries, landmarks, coordinates, and geopolitical understanding.
Claude Sonnet 4
37.0
Gemini 2.0 Flash
77.0
GPQA diamond
Claude Sonnet 4 leads by +20.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Sonnet 4
72.3
Gemini 2.0 Flash
52.2
Lech Mazur Writing
Claude Sonnet 4 leads by +9.9
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
Claude Sonnet 4
81.4
Gemini 2.0 Flash
71.5
MATH level 5
Claude Sonnet 4 leads by +2.2
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Claude Sonnet 4
84.4
Gemini 2.0 Flash
82.2
OTIS Mock AIME 2024-2025
Claude Sonnet 4 leads by +40.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 4
71.1
Gemini 2.0 Flash
31.0
SimpleBench
Claude Sonnet 4 leads by +17.3
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Sonnet 4
34.6
Gemini 2.0 Flash
17.3
The Agent Company
Claude Sonnet 4 leads by +21.7
The Agent Company · tests AI agents on realistic corporate tasks like email management, code review, data analysis, and cross-tool workflows.
Claude Sonnet 4
33.1
Gemini 2.0 Flash
11.4
WeirdML
Claude Sonnet 4 leads by +20.3
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Sonnet 4
46.1
Gemini 2.0 Flash
25.8
Full benchmark table
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash |
|---|---|---|
Aider polyglot Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework. | 61.3 | 38.2 |
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. | 5.9 | 1.3 |
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 46.9 | 61.1 |
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. | 7.3 | 1.7 |
GeoBench GeoBench · tests geographic knowledge and spatial reasoning across countries, landmarks, coordinates, and geopolitical understanding. | 37.0 | 77.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 72.3 | 52.2 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 81.4 | 71.5 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 84.4 | 82.2 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 71.1 | 31.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 34.6 | 17.3 |
The Agent Company The Agent Company · tests AI agents on realistic corporate tasks like email management, code review, data analysis, and cross-tool workflows. | 33.1 | 11.4 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 46.1 | 25.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $3.00 | $15.00 | 200K tokens (~100 books) | $60.00 | |
| $0.10 | $0.40 | 1.0M tokens (~500 books) | $1.75 |