LFM2-8B-A1B (Non-Reasoning) vs Qwen3 30B A3B 2507 Thinking
Wins 0 of 4 areas
—
Wins 4 of 4 areas
Coding · Reasoning · Facts · Following instructions
Qwen3 30B A3B 2507 Thinking 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 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.
- CodingWriting and fixing software03Qwen3 30B A3B 2507 Thinking3 of 3 tests
- ReasoningHard problems that need careful thinking02Qwen3 30B A3B 2507 Thinking2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up02Qwen3 30B A3B 2507 Thinking2 of 2 tests
- Following instructionsDoing exactly what it is asked01Qwen3 30B A3B 2507 Thinking1 of 1 test
Following instructions rests on a single test.
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 30B A3B 2507 Thinking pulls ahead
- Recent programming contest problemsLiveCodeBench v6+45points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+36.3points ahead
- Code for real scientific research problemsSciCode+26.2points ahead
Where LFM2-8B-A1B (Non-Reasoning) pulls ahead
No clear win on a test scored out of 100.
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 30B A3B 2507 Thinking
- LiveCodeBench v6Qwen3 30B A3B 2507 Thinking by 452166+45
- SciCodeQwen3 30B A3B 2507 Thinking by 26.26.833+26.2
- Terminal-Bench HardQwen3 30B A3B 2507 Thinking by 5.305.3+5.3
ReasoningQwen3 30B A3B 2507 Thinking
- GPQA DiamondQwen3 30B A3B 2507 Thinking by 36.334.470.7+36.3
- Humanity's Last ExamQwen3 30B A3B 2507 Thinking by 5.44.910.3+5.4
- CritPttie00.3tie
FactsQwen3 30B A3B 2507 Thinking
- AA-Omniscience · AccuracyQwen3 30B A3B 2507 Thinking by 8.18.216.3+8.1
- AA-Omniscience · Non-hallucinationQwen3 30B A3B 2507 Thinking by 5.87.713.5+5.8
Following instructionsQwen3 30B A3B 2507 Thinking
- IFBenchQwen3 30B A3B 2507 Thinking by 24.426.350.7+24.4
Other results11 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.
- AIME25 no toolsQwen3 30B A3B 2507 Thinking by 51.72071.7+51.7
- τ²-Bench (Retail)Qwen3 30B A3B 2507 Thinking by 49.1756.1+49.1
- MMLU-ProQwen3 30B A3B 2507 Thinking by 44.537.481.9+44.5
- BFCL v3Qwen3 30B A3B 2507 Thinking by 28.345.173.4+28.3
- BFCLv4Qwen3 30B A3B 2507 Thinking by 2525.550.5+25
- AA-OmniscienceQwen3 30B A3B 2507 Thinking by 20.4-76.5-56.1+20.4
- τ²-Bench Telecom (AA run)Qwen3 30B A3B 2507 Thinking by 17.610.528.1+17.6
- IFEvalQwen3 30B A3B 2507 Thinking by 13.277.690.8+13.2
- MATH500 (Pass@1)Qwen3 30B A3B 2507 Thinking by 11.774.886.5+11.7
- Tau² TelecomQwen3 30B A3B 2507 Thinking by 8.313.621.9+8.3
- AA IntelligenceQwen3 30B A3B 2507 Thinking by 4.94.99.8+4.9
Questions people ask
Which is better, LFM2-8B-A1B (Non-Reasoning) or Qwen3 30B A3B 2507 Thinking?
Qwen3 30B A3B 2507 Thinking wins all four areas where both have results: coding, reasoning, facts and following instructions. LFM2-8B-A1B (Non-Reasoning) wins none.
Which is better for coding?
Qwen3 30B A3B 2507 Thinking. It wins 3 of the 3 coding tests both models report; LFM2-8B-A1B (Non-Reasoning) wins none.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 9 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 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.