Claude 3 Haiku vs Kimi Linear 48B A3B Instruct
Wins 1 of 4 areas
Following instructions
Wins 1 of 4 areas
Coding
The two are evenly matched.Claude 3 Haiku is better at following instructions; Kimi Linear 48B A3B Instruct at coding.
Scores updated · 9 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.
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 Kimi Linear 48B A3B Instruct pulls ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+10.6points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.8points ahead
- Code for real scientific research problemsSciCode+1.3points ahead
Where Claude 3 Haiku pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+8points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+1.6points ahead
Every test, side by side
All 9 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi Linear 48B A3B Instruct
- Terminal-Bench HardKimi Linear 48B A3B Instruct by 10.60.811.4+10.6
- SciCodeKimi Linear 48B A3B Instruct by 1.318.619.9+1.3
ReasoningEven
- GPQA DiamondKimi Linear 48B A3B Instruct by 3.837.441.2+3.8
- Humanity's Last ExamClaude 3 Haiku by 1.64.12.5+1.6
Following instructionsClaude 3 Haiku
- IFBenchClaude 3 Haiku by 836.128.1+8
Other results3 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 Haiku by 21.121.10+21.1
- Artificial Analysis Coding IndexKimi Linear 48B A3B Instruct by 7.56.714.2+7.5
- AA IntelligenceKimi Linear 48B A3B Instruct by 1.75.67.3+1.7
Questions people ask
Which is better, Claude 3 Haiku or Kimi Linear 48B A3B Instruct?
Claude 3 Haiku and Kimi Linear 48B A3B Instruct each win one of the four areas where both have results. Claude 3 Haiku wins following instructions; Kimi Linear 48B A3B Instruct wins coding. They are level on reasoning and long documents.
Which is better for coding?
Kimi Linear 48B A3B Instruct. It wins 2 of the 2 coding tests both models report; Claude 3 Haiku wins none.
How do you compare the two?
We use the 9 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 3 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.