Claude 3 Haiku vs Motif-2-12.7B-Reasoning
Wins 2 of 6 areas
Facts · Long documents
Wins 3 of 6 areas
Coding · Reasoning · Following instructions
Motif-2-12.7B-Reasoning wins more areas, narrowly.Claude 3 Haiku is better at facts.
Scores updated · 15 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.
- ReasoningHard problems that need careful thinking02Motif-2-12.7B-Reasoning2 of 3 tests · 1 tie
- CodingWriting and fixing software02Motif-2-12.7B-Reasoning2 of 2 tests
- Following instructionsDoing exactly what it is asked01Motif-2-12.7B-Reasoning1 of 1 test
- FactsGetting facts right instead of making them up20Claude 3 Haiku2 of 2 tests
- Long documentsFinding answers in very long texts10Claude 3 Haiku1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 1 tie
Agents, 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 three tests each model wins by the widest margin. Scores are out of 100.
Where Motif-2-12.7B-Reasoning pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+32.1points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+20.9points ahead
- Code for real scientific research problemsSciCode+9.6points ahead
Where Claude 3 Haiku pulls ahead
- Reasons across sets of long documentsAA-LCR+13points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+10.1points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+2.4points ahead
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMotif-2-12.7B-Reasoning
- SciCodeMotif-2-12.7B-Reasoning by 9.618.628.2+9.6
- Terminal-Bench HardMotif-2-12.7B-Reasoning by 30.83.8+3
ReasoningMotif-2-12.7B-Reasoning
- GPQA DiamondMotif-2-12.7B-Reasoning by 32.137.469.5+32.1
- Humanity's Last ExamMotif-2-12.7B-Reasoning by 4.74.18.8+4.7
- CritPttie00tie
FactsClaude 3 Haiku
- AA-Omniscience · Non-hallucinationClaude 3 Haiku by 10.119.59.4+10.1
- AA-Omniscience · AccuracyClaude 3 Haiku by 2.417.615.2+2.4
Following instructionsMotif-2-12.7B-Reasoning
- IFBenchMotif-2-12.7B-Reasoning by 20.936.157+20.9
Other results5 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)Motif-2-12.7B-Reasoning by 25.421.146.5+25.4
- AA-OmniscienceClaude 3 Haiku by 13.1-48.6-61.7+13.1
- AA Agentic IndexMotif-2-12.7B-Reasoning by 12.2719.2+12.2
- Artificial Analysis Coding IndexMotif-2-12.7B-Reasoning by 5.26.711.9+5.2
- AA IntelligenceMotif-2-12.7B-Reasoning by 3.65.69.2+3.6
Questions people ask
Which is better, Claude 3 Haiku or Motif-2-12.7B-Reasoning?
Motif-2-12.7B-Reasoning wins three of the six areas where both have results: coding, reasoning and following instructions. Claude 3 Haiku wins facts and long documents. They are level on agents.
Which is better for coding?
Motif-2-12.7B-Reasoning. 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 15 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 5 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.