LFM2.5-2.6B vs Qwen3.5 397B A17B
Wins 0 of 6 areas
—
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Qwen3.5 397B A17B is the stronger all-rounder.
Scores updated · 20 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 software03Qwen3.5 397B A17B3 of 3 tests
- ReasoningHard problems that need careful thinking03Qwen3.5 397B A17B3 of 3 tests
- AgentsCarrying out multi-step tasks on its own02Qwen3.5 397B A17B2 of 2 tests
- Long documentsFinding answers in very long texts01Qwen3.5 397B A17B1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.5 397B A17B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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 Qwen3.5 397B A17B pulls ahead
- Reasons across sets of long documentsAA-LCR+71.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+46.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+33.5points ahead
Where LFM2.5-2.6B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+72.9points ahead
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 397B A17B
- Terminal-Bench 2.1Qwen3.5 397B A17B by 46.84.551.3+46.8
- SciCodeQwen3.5 397B A17B by 30.414.444.8+30.4
- LiveCodeBench v6Qwen3.5 397B A17B by 24.259.483.6+24.2
AgentsQwen3.5 397B A17B
- GDPValQwen3.5 397B A17B by 14.8014.8+14.8
- τ-Bench V3 · BankingQwen3.5 397B A17B by 6.27.213.4+6.2
ReasoningQwen3.5 397B A17B
- GPQA DiamondQwen3.5 397B A17B by 33.555.889.3+33.5
- Humanity's Last ExamQwen3.5 397B A17B by 22.86.229+22.8
- CritPtQwen3.5 397B A17B by 1.701.7+1.7
FactsEven
- AA-Omniscience · Non-hallucinationLFM2.5-2.6B by 72.98411.1+72.9
- AA-Omniscience · AccuracyQwen3.5 397B A17B by 26.44.330.8+26.4
Long documentsQwen3.5 397B A17B
- AA-LCRQwen3.5 397B A17B by 71.65.777.3+71.6
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 19.659.278.8+19.6
Other results8 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.
- Artificial Analysis Coding IndexQwen3.5 397B A17B by 40.57.748.2+40.5
- AA-OmniscienceLFM2.5-2.6B by 19.8-10.9-30.8+19.8
- PinchBenchQwen3.5 397B A17B by 18.468.286.6+18.4
- BFCLv4Qwen3.5 397B A17B by 1656.972.9+16
- AA IntelligenceQwen3.5 397B A17B by 108.418.4+10
- AA Agentic IndexQwen3.5 397B A17B by 8.22.410.6+8.2
- Claw-Eval AvgQwen3.5 397B A17B by 7.862.970.7+7.8
- τ³-Bench BankingQwen3.5 397B A17B by 7.75.713.4+7.7
Questions people ask
Which is better, LFM2.5-2.6B or Qwen3.5 397B A17B?
Qwen3.5 397B A17B wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. LFM2.5-2.6B wins none. They are level on facts.
Which is better for coding?
Qwen3.5 397B A17B. It wins 3 of the 3 coding tests both models report; LFM2.5-2.6B wins none.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.