Compare · ModelsLive · 2 picked · head to head
Claude Haiku 4.5 vs GPT-4.1 Mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Haiku 4.5 wins on 11/11 benchmarks
Claude Haiku 4.5 wins 11 of 11 shared benchmarks. Leads in reasoning · knowledge · general.
Category leads
reasoning·Claude Haiku 4.5knowledge·Claude Haiku 4.5general·Claude Haiku 4.5math·Claude Haiku 4.5coding·Claude Haiku 4.5
Hype vs Reality
Attention vs performance
Claude Haiku 4.5
#231 by perf·#13 by attention
GPT-4.1 Mini
#211 by perf·no signal
Best value
GPT-4.1 Mini
3.2x better value than Claude Haiku 4.5
Claude Haiku 4.5
11.3 pts/$
$3.00/M
GPT-4.1 Mini
36.6 pts/$
$1.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
11 benchmarks · 2 models
Claude Haiku 4.5GPT-4.1 Mini
ARC-AGI
Claude Haiku 4.5 leads by +44.2
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-4.1 Mini
3.5
ARC-AGI-2
Claude Haiku 4.5 leads by +4.0
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-4.1 Mini
0.0
Chess Puzzles
Claude Haiku 4.5 leads by +1.1
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-4.1 Mini
2.1
Dtbench
Claude Haiku 4.5 leads by +8.0
Claude Haiku 4.5
56.0
GPT-4.1 Mini
48.0
FrontierMath-2025-02-28-Private
Claude Haiku 4.5 leads by +5.9
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-4.1 Mini
4.5
GPQA diamond
Claude Haiku 4.5 leads by +7.2
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-4.1 Mini
54.5
Lmca
Claude Haiku 4.5 leads by +11.5
Claude Haiku 4.5
36.4
GPT-4.1 Mini
24.9
MATH level 5
Claude Haiku 4.5 leads by +9.1
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-4.1 Mini
87.3
OTIS Mock AIME 2024-2025
Claude Haiku 4.5 leads by +22.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Haiku 4.5
66.6
GPT-4.1 Mini
44.7
SimpleQA Verified
Claude Haiku 4.5 leads by +0.5
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-4.1 Mini
12.7
WeirdML
Claude Haiku 4.5 leads by +7.8
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-4.1 Mini
37.6
Full benchmark table
| Benchmark | Claude Haiku 4.5 | GPT-4.1 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 | 3.5 |
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 | 0.0 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 3.2 | 2.1 |
Dtbench | 56.0 | 48.0 |
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 | 4.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 61.6 | 54.5 |
Lmca | 36.4 | 24.9 |
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 | 87.3 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 66.6 | 44.7 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 13.2 | 12.7 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 45.4 | 37.6 |
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 | |
| $0.40 | $1.60 | 1.0M tokens (~524 books) | $7.00 |
People also compared