Granite 4.0 H Tiny vs Qwen3 30B A3B 2507 Thinking
Wins 0 of 4 areas
—
Wins 4 of 4 areas
Coding · Reasoning · Math · Following instructions
Qwen3 30B A3B 2507 Thinking is the stronger all-rounder.
Scores updated · 12 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 software01Qwen3 30B A3B 2507 Thinking1 of 1 test
- ReasoningHard problems that need careful thinking01Qwen3 30B A3B 2507 Thinking1 of 1 test
- MathCompetition and research-level math01Qwen3 30B A3B 2507 Thinking1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3 30B A3B 2507 Thinking1 of 1 test
Coding, reasoning, math 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 30B A3B 2507 Thinking pulls ahead
- US invitational high-school math exam problemsAIME 2026+85points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+44.2points ahead
- Recent programming contest problemsLiveCodeBench v6+39.3points ahead
Where Granite 4.0 H Tiny pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 12 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 39.326.766+39.3
ReasoningQwen3 30B A3B 2507 Thinking
- GPQA DiamondQwen3 30B A3B 2507 Thinking by 44.226.570.7+44.2
MathQwen3 30B A3B 2507 Thinking
- AIME 2026Qwen3 30B A3B 2507 Thinking by 853.388.3+85
Following instructionsQwen3 30B A3B 2507 Thinking
- IFBenchQwen3 30B A3B 2507 Thinking by 32.318.450.7+32.3
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.
- AIME25 no toolsQwen3 30B A3B 2507 Thinking by 66.84.971.7+66.8
- MMLU-ProQwen3 30B A3B 2507 Thinking by 49.93281.9+49.9
- τ²-Bench (Retail)Qwen3 30B A3B 2507 Thinking by 37.718.456.1+37.7
- MATH500 (Pass@1)Qwen3 30B A3B 2507 Thinking by 27.359.286.5+27.3
- BFCLv4Qwen3 30B A3B 2507 Thinking by 2228.550.5+22
- BFCL v3Qwen3 30B A3B 2507 Thinking by 16.556.973.4+16.5
- IFEvalQwen3 30B A3B 2507 Thinking by 9.781.190.8+9.7
- Tau² TelecomQwen3 30B A3B 2507 Thinking by 5.216.721.9+5.2
Questions people ask
Which is better, Granite 4.0 H Tiny or Qwen3 30B A3B 2507 Thinking?
Qwen3 30B A3B 2507 Thinking wins all four areas where both have results: coding, reasoning, math and following instructions. Granite 4.0 H Tiny wins none.
Which is better for coding?
Qwen3 30B A3B 2507 Thinking. It wins the one coding test both models report.
How do you compare the two?
We use the 12 benchmark tests both models have published scores on. The verdict counts the 4 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.