Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 4.6 vs o4 Mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 4.6 wins on 11/12 benchmarks
Claude Sonnet 4.6 wins 11 of 12 shared benchmarks. Leads in reasoning · knowledge · general.
Category leads
reasoning·Claude Sonnet 4.6knowledge·Claude Sonnet 4.6general·Claude Sonnet 4.6math·Claude Sonnet 4.6coding·Claude Sonnet 4.6
Hype vs Reality
Attention vs performance
Claude Sonnet 4.6
#169 by perf·#11 by attention
o4 Mini
#144 by perf·no signal
Best value
o4 Mini
3.5x better value than Claude Sonnet 4.6
Claude Sonnet 4.6
5.0 pts/$
$9.00/M
o4 Mini
17.7 pts/$
$2.75/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
12 benchmarks · 2 models
Claude Sonnet 4.6o4 Mini
ARC-AGI
Claude Sonnet 4.6 leads by +27.8
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Sonnet 4.6
86.5
o4 Mini
58.7
ARC-AGI-2
Claude Sonnet 4.6 leads by +54.3
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 4.6
60.4
o4 Mini
6.1
Chess Puzzles
o4 Mini leads by +4.9
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Sonnet 4.6
13.0
o4 Mini
17.9
Dtbench
Claude Sonnet 4.6 leads by +20.5
Claude Sonnet 4.6
83.1
o4 Mini
62.7
FrontierMath-2025-02-28-Private
Claude Sonnet 4.6 leads by +7.6
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Claude Sonnet 4.6
32.4
o4 Mini
24.8
FrontierMath-Tier-4-2025-07-01-Private
Claude Sonnet 4.6 leads by +7.6
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
Claude Sonnet 4.6
13.8
o4 Mini
6.3
GPQA diamond
Claude Sonnet 4.6 leads by +10.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Sonnet 4.6
86.6
o4 Mini
75.8
Lmca
Claude Sonnet 4.6 leads by +23.5
Claude Sonnet 4.6
54.7
o4 Mini
31.2
Mystery Game Puzzles
Claude Sonnet 4.6 leads by +7.5
Claude Sonnet 4.6
7.5
o4 Mini
0.0
OTIS Mock AIME 2024-2025
Claude Sonnet 4.6 leads by +4.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 4.6
85.8
o4 Mini
81.7
SimpleQA Verified
Claude Sonnet 4.6 leads by +11.6
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Sonnet 4.6
35.5
o4 Mini
23.9
WeirdML
Claude Sonnet 4.6 leads by +13.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Sonnet 4.6
66.1
o4 Mini
52.6
Full benchmark table
| Benchmark | Claude Sonnet 4.6 | o4 Mini |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 86.5 | 58.7 |
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. | 60.4 | 6.1 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 13.0 | 17.9 |
Dtbench | 83.1 | 62.7 |
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. | 32.4 | 24.8 |
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. | 13.8 | 6.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 86.6 | 75.8 |
Lmca | 54.7 | 31.2 |
Mystery Game Puzzles | 7.5 | 0.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 85.8 | 81.7 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 35.5 | 23.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 66.1 | 52.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $3.00 | $15.00 | 1.0M tokens (~500 books) | $60.00 | |
| $1.10 | $4.40 | 200K tokens (~100 books) | $19.25 |
People also compared