Compare · ModelsLive · 2 picked · head to head
Claude Haiku 4.5 vs GPT-5 Mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5 Mini wins on 12/13 benchmarks
GPT-5 Mini wins 12 of 13 shared benchmarks. Leads in reasoning · knowledge · general.
Category leads
reasoning·GPT-5 Miniknowledge·GPT-5 Minigeneral·GPT-5 Minimath·GPT-5 Minicoding·Claude Haiku 4.5
Hype vs Reality
Attention vs performance
Claude Haiku 4.5
#231 by perf·#13 by attention
GPT-5 Mini
#108 by perf·#4 by attention
Best value
GPT-5 Mini
4.0x better value than Claude Haiku 4.5
Claude Haiku 4.5
11.3 pts/$
$3.00/M
GPT-5 Mini
45.8 pts/$
$1.13/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
13 benchmarks · 2 models
Claude Haiku 4.5GPT-5 Mini
ARC-AGI
GPT-5 Mini leads by +6.7
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Haiku 4.5
47.7
GPT-5 Mini
54.3
ARC-AGI-2
GPT-5 Mini leads by +0.4
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Haiku 4.5
4.0
GPT-5 Mini
4.4
Chess Puzzles
GPT-5 Mini leads by +23.2
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Haiku 4.5
3.2
GPT-5 Mini
26.4
Dtbench
GPT-5 Mini leads by +11.5
Claude Haiku 4.5
56.0
GPT-5 Mini
67.5
FrontierMath-2025-02-28-Private
GPT-5 Mini leads by +16.9
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Claude Haiku 4.5
10.4
GPT-5 Mini
27.2
FrontierMath-Tier-4-2025-07-01-Private
GPT-5 Mini leads by +4.2
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
Claude Haiku 4.5
2.1
GPT-5 Mini
6.3
GPQA diamond
GPT-5 Mini leads by +5.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Haiku 4.5
61.6
GPT-5 Mini
66.7
Lmca
GPT-5 Mini leads by +3.8
Claude Haiku 4.5
36.4
GPT-5 Mini
40.2
MATH level 5
GPT-5 Mini leads by +1.5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Claude Haiku 4.5
96.4
GPT-5 Mini
97.8
OTIS Mock AIME 2024-2025
GPT-5 Mini leads by +20.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Haiku 4.5
66.6
GPT-5 Mini
86.7
SimpleQA Verified
GPT-5 Mini leads by +8.4
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Haiku 4.5
13.2
GPT-5 Mini
21.6
Terminal Bench
Claude Haiku 4.5 leads by +0.7
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence.
Claude Haiku 4.5
35.5
GPT-5 Mini
34.8
WeirdML
GPT-5 Mini leads by +7.3
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Claude Haiku 4.5
45.4
GPT-5 Mini
52.7
Full benchmark table
| Benchmark | Claude Haiku 4.5 | GPT-5 Mini |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 47.7 | 54.3 |
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. | 4.0 | 4.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 3.2 | 26.4 |
Dtbench | 56.0 | 67.5 |
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. | 10.4 | 27.2 |
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. | 2.1 | 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. | 61.6 | 66.7 |
Lmca | 36.4 | 40.2 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 96.4 | 97.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 66.6 | 86.7 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 13.2 | 21.6 |
Terminal Bench Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence. | 35.5 | 34.8 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 45.4 | 52.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.00 | $5.00 | 200K tokens (~100 books) | $20.00 | |
| $0.25 | $2.00 | 400K tokens (~200 books) | $6.88 |