Claude 3.5 Haiku vs GPT-4o mini
Wins 4 of 6 areas
Coding · Agents · Images and charts · Following instructions
Wins 2 of 6 areas
Reasoning · Facts
Claude 3.5 Haiku is the stronger all-rounder.GPT-4o mini is better at reasoning.
Scores updated · 24 tests both models report · How we compare
Where each one wins
Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software30Claude 3.5 Haiku3 of 3 tests
- AgentsCarrying out multi-step tasks on its own10Claude 3.5 Haiku1 of 2 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video10Claude 3.5 Haiku1 of 1 test
- Following instructionsDoing exactly what it is asked10Claude 3.5 Haiku1 of 1 test
- ReasoningHard problems that need careful thinking01GPT-4o mini1 of 2 tests · 1 tie
- FactsGetting facts right instead of making them up01GPT-4o mini1 of 1 test
Facts, images and charts and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude 3.5 Haiku pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+31.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+11.8points ahead
- Code for real scientific research problemsSciCode+4.5points ahead
Where GPT-4o mini pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+1.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+1.6points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude 3.5 Haiku
- SWE-bench VerifiedClaude 3.5 Haiku by 31.940.68.7+31.9
- SciCodeClaude 3.5 Haiku by 4.527.422.9+4.5
- Terminal-Bench 2.1Claude 3.5 Haiku by 4.510.15.6+4.5
AgentsClaude 3.5 Haiku
- τ-Bench V3 · BankingClaude 3.5 Haiku by 2.95.82.9+2.9
- GDPValtie00tie
ReasoningGPT-4o mini
- GPQA DiamondGPT-4o mini by 1.840.842.6+1.8
- Humanity's Last Examtie3.64.2tie
Images and chartsClaude 3.5 Haiku
- MMMU-ProClaude 3.5 Haiku by 4.145.641.5+4.1
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 11.842.831+11.8
Other results14 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- Aider-PolyglotClaude 3.5 Haiku by 24.4283.6+24.4
- MATHClaude 3.5 Haiku by 787.280.2+7
- OpenBookQAGPT-4o mini by 6.685.492+6.6
- Artificial Analysis Coding IndexClaude 3.5 Haiku by 4.515.911.4+4.5
- naturalquestions_closedbookGPT-4o mini by 4.234.438.5+4.2
- DROPClaude 3.5 Haiku by 3.483.179.7+3.4
- MMLU-ProClaude 3.5 Haiku by 3.36561.7+3.3
- GSM8KGPT-4o mini by 2.881.584.3+2.8
- AA IntelligenceClaude 3.5 Haiku by 2.28.96.7+2.2
- MGSMGPT-4o mini by 1.485.687+1.4
- HumanEvaltie88.187.2tie
- MBPPtie85.684.8tie
- NarrativeQAtie76.376.8tie
- MMLUtie67.166.8tie
Questions people ask
Which is better, Claude 3.5 Haiku or GPT-4o mini?
Claude 3.5 Haiku wins four of the six areas where both have results: coding, agents, images and charts and following instructions. GPT-4o mini wins reasoning and facts.
Which is better for coding?
Claude 3.5 Haiku. It wins 3 of the 3 coding tests both models report; GPT-4o mini wins none.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.