Claude 3.5 Haiku vs OLMo-2-7B
Wins 3 of 4 areas
Coding · Long documents · Following instructions
Wins 0 of 4 areas
—
Claude 3.5 Haiku is the stronger all-rounder.
Scores updated · 8 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
Long documents and following instructions rest on a single test each.
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
- Code for real scientific research problemsSciCode+23.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+18.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+12points ahead
Where OLMo-2-7B pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.8points ahead
Every test, side by side
All 8 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude 3.5 Haiku
- SciCodeClaude 3.5 Haiku by 23.727.43.7+23.7
- Terminal-Bench HardClaude 3.5 Haiku by 2.32.30+2.3
ReasoningEven
- GPQA DiamondClaude 3.5 Haiku by 1240.828.8+12
- Humanity's Last ExamOLMo-2-7B by 1.83.65.4+1.8
Following instructionsClaude 3.5 Haiku
- IFBenchClaude 3.5 Haiku by 18.442.824.4+18.4
Other results2 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.
- τ²-Bench Telecom (AA run)Claude 3.5 Haiku by 24.624.60+24.6
- AA IntelligenceClaude 3.5 Haiku by 3.38.95.6+3.3
Questions people ask
Which is better, Claude 3.5 Haiku or OLMo-2-7B?
Claude 3.5 Haiku wins three of the four areas where both have results: coding, long documents and following instructions. OLMo-2-7B wins none. They are level on reasoning.
Which is better for coding?
Claude 3.5 Haiku. It wins 2 of the 2 coding tests both models report; OLMo-2-7B wins none.
How do you compare the two?
We use the 8 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 2 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.