Qwen3.5 9B wins more areas, narrowly.LFM3-1.7B is better at following instructions.
Scores updated · 20 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.
Agents 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 9B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+17.2points ahead
- Multi-step tasks using many real software toolsMCP Atlas+10.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+7.7points ahead
Where LFM3-1.7B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+7.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+6.3points 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.
CodingEven
- LiveCodeBench v6LFM3-1.7B by 7.973.565.6+7.9
- SciCodeQwen3.5 9B by 128.529.5+1
ReasoningQwen3.5 9B
- GPQA DiamondQwen3.5 9B by 17.263.480.6+17.2
- Humanity's Last ExamQwen3.5 9B by 7.77.214.9+7.7
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.
- AutomationBench PublicLFM3-1.7B by 26.241.315.1+26.2
- RULER 128KQwen3.5 9B by 21.565.687.1+21.5
- SWE-bench Multilingual (OpenCode)Qwen3.5 9B by 122335+12
- BFCLv4LFM3-1.7B by 11.371.460.1+11.3
- WebArena-VerifiedLFM3-1.7B by 9.538.428.9+9.5
- IFEvalLFM3-1.7B by 5.296.791.5+5.2
- Terminal-Bench 2.1 (OpenCode)Qwen3.5 9B by 5.112.918+5.1
- HLE (with tools)Qwen3.5 9B by 3.613.917.5+3.6
- LiveCodeBench Pro 25Q2Qwen3.5 9B by 2.731.734.4+2.7
- Claw-Eval General (EN), averageLFM3-1.7B by 2.168.666.5+2.1
- BrowseComp-Plus (OpenClaw subset)Qwen3.5 9B by 13738+1
- τ³-bench (4 domains), averagetie6867.1tie
- EnterpriseOps-Gymtie28.229tie
- Claw-Eval General (EN), pass^3tie51.451.9tie
Questions people ask
Which is better, LFM3-1.7B or Qwen3.5 9B?
Qwen3.5 9B wins two of the four areas where both have results: agents and reasoning. LFM3-1.7B wins following instructions. They are level on coding.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
How do you compare the two?
We use the 20 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 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.