Gemma 4 26B A4B vs Qwen3.7 Plus Preview
Wins 0 of 8 areas
—
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Qwen3.7 Plus Preview is the stronger all-rounder.Gemma 4 26B A4B is cheaper.
Scores updated · 46 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 software07Qwen3.7 Plus Preview7 of 7 tests
- AgentsCarrying out multi-step tasks on its own03Qwen3.7 Plus Preview3 of 3 tests
- ReasoningHard problems that need careful thinking03Qwen3.7 Plus Preview3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03Qwen3.7 Plus Preview3 of 3 tests
- FactsGetting facts right instead of making them up02Qwen3.7 Plus Preview2 of 2 tests
- MathCompetition and research-level math02Qwen3.7 Plus Preview2 of 2 tests
- Long documentsFinding answers in very long texts01Qwen3.7 Plus Preview1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.7 Plus Preview1 of 1 test
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 74% 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 Qwen3.7 Plus Preview pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+60.3points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+58.7points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+58.5points ahead
Where Gemma 4 26B A4B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 46 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Plus Preview
- SWE-bench VerifiedQwen3.7 Plus Preview by 60.317.477.7+60.3
- SWE-bench MultilingualQwen3.7 Plus Preview by 58.517.375.8+58.5
- SWE-bench ProQwen3.7 Plus Preview by 43.813.857.6+43.8
- Terminal-Bench HardQwen3.7 Plus Preview by 33.413.647+33.4
- Terminal-Bench 2.1Qwen3.7 Plus Preview by 223961+22
- LiveCodeBench v6Qwen3.7 Plus Preview by 12.577.189.6+12.5
- SciCodeQwen3.7 Plus Preview by 6.14046.1+6.1
AgentsQwen3.7 Plus Preview
- MCP AtlasQwen3.7 Plus Preview by 23.25073.2+23.2
- GDPValQwen3.7 Plus Preview by 10.13.313.4+10.1
- τ-Bench V3 · BankingQwen3.7 Plus Preview by 5.51217.5+5.5
ReasoningQwen3.7 Plus Preview
- Humanity's Last ExamQwen3.7 Plus Preview by 16.319.335.6+16.3
- GPQA DiamondQwen3.7 Plus Preview by 10.879.290+10.8
- CritPtQwen3.7 Plus Preview by 9.109.1+9.1
FactsQwen3.7 Plus Preview
- AA-Omniscience · Non-hallucinationQwen3.7 Plus Preview by 58.713.672.3+58.7
- AA-Omniscience · AccuracyQwen3.7 Plus Preview by 3.419.122.5+3.4
Images and chartsQwen3.7 Plus Preview
- CharXiv (RQ)Qwen3.7 Plus Preview by 16.96985.9+16.9
- MMMU-ProQwen3.7 Plus Preview by 11.369.280.5+11.3
- LMArena · VisionQwen3.7 Plus Preview by 17 rating points12601277+17 rating
MathQwen3.7 Plus Preview
- HMMT Feb. 2026Qwen3.7 Plus Preview by 13.97992.9+13.9
- IMOAnswerBenchQwen3.7 Plus Preview by 11.774.386+11.7
Long documentsQwen3.7 Plus Preview
- AA-LCRQwen3.7 Plus Preview by 7.365.773+7.3
Following instructionsQwen3.7 Plus Preview
- IFBenchQwen3.7 Plus Preview by 5.672.478+5.6
Other results24 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.
- AA-OmniscienceQwen3.7 Plus Preview by 51.9-50.81.1+51.9
- τ²-Bench Telecom (AA run)Qwen3.7 Plus Preview by 49.443.693+49.4
- DeepPlanningQwen3.7 Plus Preview by 46.116.262.3+46.1
- MCPMarkQwen3.7 Plus Preview by 44.514.258.7+44.5
- Terminal-Bench 2.0Qwen3.7 Plus Preview by 36.134.270.3+36.1
- Claw Eval (pass@3)Qwen3.7 Plus Preview by 34.72862.7+34.7
- NL2RepoQwen3.7 Plus Preview by 29.511.641.1+29.5
- SimpleVQAQwen3.7 Plus Preview by 29.552.281.7+29.5
- QwenClawBenchQwen3.7 Plus Preview by 23.138.761.8+23.1
- OmniDocBench 1.5Qwen3.7 Plus Preview by 1774.491.4+17
- Artificial Analysis Coding IndexQwen3.7 Plus Preview by 16.639.355.9+16.6
- BFCLv4Qwen3.7 Plus Preview by 15.857.172.9+15.8
- RealWorldQAQwen3.7 Plus Preview by 14.772.286.9+14.7
- MedXPertQA MMQwen3.7 Plus Preview by 12.958.171+12.9
- SuperGPQAQwen3.7 Plus Preview by 1061.471.4+10
- AA Agentic IndexQwen3.7 Plus Preview by 8.71119.7+8.7
- VITA-BenchQwen3.7 Plus Preview by 8.736.945.6+8.7
- AA IntelligenceQwen3.7 Plus Preview by 8.516.725.2+8.5
- MATH-VisionQwen3.7 Plus Preview by 7.982.490.3+7.9
- HLE-DiamondQwen3.7 Plus Preview by 7.76.213.9+7.7
- MMLU-ProQwen3.7 Plus Preview by 5.982.688.5+5.9
- MMMLUQwen3.7 Plus Preview by 2.786.389+2.7
- IFEvalQwen3.7 Plus Preview by 2.69294.6+2.6
- MMLU-ReduxQwen3.7 Plus Preview by 1.892.794.5+1.8
Questions people ask
Which is better, Gemma 4 26B A4B or Qwen3.7 Plus Preview?
Qwen3.7 Plus Preview wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Gemma 4 26B A4B wins none, but costs 74% less.
Which is better for coding?
Qwen3.7 Plus Preview. It wins 7 of the 7 coding tests both models report; Gemma 4 26B A4B wins none.
Which is cheaper?
Gemma 4 26B A4B costs $0.12 per million input tokens and $0.40 per million output tokens; Qwen3.7 Plus Preview costs $0.40 and $1.60. That makes Gemma 4 26B A4B about 74% cheaper for the same work.
How do you compare the two?
We use the 46 benchmark tests both models have published scores on. The verdict counts the 22 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 24 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.