Gemma 4 26B A4B vs Qwen3 Max (Reasoning)
Wins 1 of 7 areas
Following instructions
Wins 5 of 7 areas
Coding · Agents · Reasoning · Math · Long documents
Qwen3 Max (Reasoning) is the stronger all-rounder.Gemma 4 26B A4B is cheaper and better at following instructions.
Scores updated · 28 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software04Qwen3 Max (Reasoning)4 of 4 tests
- ReasoningHard problems that need careful thinking03Qwen3 Max (Reasoning)3 of 3 tests
- MathCompetition and research-level math02Qwen3 Max (Reasoning)2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3 Max (Reasoning)1 of 1 test
- Long documentsFinding answers in very long texts01Qwen3 Max (Reasoning)1 of 1 test
- Following instructionsDoing exactly what it is asked10Gemma 4 26B A4B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
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.
Gemma 4 26B A4B costs 93% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3 Max (Reasoning) pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+57.9points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+49.4points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+27.6points ahead
Where Gemma 4 26B A4B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+1.7points ahead
Every test, side by side
All 28 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3 Max (Reasoning)
- SWE-bench VerifiedQwen3 Max (Reasoning) by 57.917.475.3+57.9
- SWE-bench MultilingualQwen3 Max (Reasoning) by 49.417.366.7+49.4
- Terminal-Bench HardQwen3 Max (Reasoning) by 10.613.624.2+10.6
- LiveCodeBench v6Qwen3 Max (Reasoning) by 8.877.185.9+8.8
ReasoningQwen3 Max (Reasoning)
- Humanity's Last ExamQwen3 Max (Reasoning) by 8.719.328+8.7
- GPQA DiamondQwen3 Max (Reasoning) by 6.979.286.1+6.9
- CritPtQwen3 Max (Reasoning) by 1.701.7+1.7
FactsEven
- AA-Omniscience · AccuracyQwen3 Max (Reasoning) by 10.719.129.8+10.7
- AA-Omniscience · Non-hallucinationGemma 4 26B A4B by 8.313.65.3+8.3
MathQwen3 Max (Reasoning)
- IMOAnswerBenchQwen3 Max (Reasoning) by 9.674.383.9+9.6
- AIME 2026Qwen3 Max (Reasoning) by 588.393.3+5
Long documentsQwen3 Max (Reasoning)
- AA-LCRQwen3 Max (Reasoning) by 8.665.774.3+8.6
Following instructionsGemma 4 26B A4B
- IFBenchGemma 4 26B A4B by 1.772.470.7+1.7
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.
- τ²-Bench Telecom (AA run)Qwen3 Max (Reasoning) by 4043.683.6+40
- WideSearchQwen3 Max (Reasoning) by 19.638.357.9+19.6
- MCPMarkQwen3 Max (Reasoning) by 19.314.233.5+19.3
- AA-OmniscienceQwen3 Max (Reasoning) by 14.2-50.8-36.6+14.2
- DeepPlanningQwen3 Max (Reasoning) by 12.516.228.7+12.5
- Terminal-Bench 2.0Gemma 4 26B A4B by 11.734.222.5+11.7
- C-EvalQwen3 Max (Reasoning) by 11.282.593.7+11.2
- t2-benchGemma 4 26B A4B by 10.785.574.8+10.7
- SuperGPQAQwen3 Max (Reasoning) by 5.961.467.3+5.9
- AA IntelligenceQwen3 Max (Reasoning) by 4.616.721.3+4.6
- VITA-BenchQwen3 Max (Reasoning) by 436.940.9+4
- MMLU-ProQwen3 Max (Reasoning) by 3.182.685.7+3.1
- MMMLUGemma 4 26B A4B by 1.986.384.4+1.9
- MMLU-Reduxtie92.792.8tie
Questions people ask
Which is better, Gemma 4 26B A4B or Qwen3 Max (Reasoning)?
Qwen3 Max (Reasoning) wins five of the seven areas where both have results: coding, agents, reasoning, math and long documents. Gemma 4 26B A4B wins following instructions, and costs 93% less. They are level on facts.
Which is better for coding?
Qwen3 Max (Reasoning). It wins 4 of the 4 coding tests both models report; Gemma 4 26B A4B wins none.
Which is cheaper?
Gemma 4 26B A4B costs $0.13 per million input tokens and $0.40 per million output tokens; Qwen3 Max (Reasoning) costs $1.20 and $6.00. That makes Gemma 4 26B A4B about 93% cheaper for the same work.
How do you compare the two?
We use the 28 benchmark tests both models have published scores on. The verdict counts the 14 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.