Kimi K2.7 Code vs Qwen3.7 Max
Wins 0 of 7 areas
—
Wins 5 of 7 areas
Coding · Reasoning · Facts · Math · Following instructions
Qwen3.7 Max is the stronger all-rounder.Kimi K2.7 Code is cheaper.
Scores updated · 35 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.
- ReasoningHard problems that need careful thinking04Qwen3.7 Max4 of 5 tests · 1 tie
- CodingWriting and fixing software14Qwen3.7 Max4 of 6 tests · 1 tie
- MathCompetition and research-level math03Qwen3.7 Max3 of 3 tests
- Following instructionsDoing exactly what it is asked02Qwen3.7 Max2 of 2 tests
- FactsGetting facts right instead of making them up12Qwen3.7 Max2 of 3 tests
- AgentsCarrying out multi-step tasks on its own11Even1 each · 2 ties
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Long documents 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.
Kimi K2.7 Code costs 51% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.7 Max pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+56.8points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+22points ahead
- Short factual questions, answered correctlySimpleQA Verified+19.3points ahead
Where Kimi K2.7 Code pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+8.5points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+8.4points ahead
- Fixes real GitHub issues, working as an agentLiveBench · Agentic Coding+2.1points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.7 Max
- Terminal-Bench 2.1Qwen3.7 Max by 7.167.474.5+7.1
- Terminal-Bench HardQwen3.7 Max by 6.144.750.8+6.1
- LMArena · WebDevQwen3.7 Max by 42 rating points14731515+42 rating
- LiveBench · Agentic CodingKimi K2.7 Code by 2.145.743.6+2.1
- SciCodeQwen3.7 Max by 1.747.849.5+1.7
- LiveBench · Codingtie7474.2tie
AgentsEven
- τ-Bench V3 · BankingKimi K2.7 Code by 8.420.211.8+8.4
- GDPValQwen3.7 Max by 4.62731.6+4.6
- Terminal-Bench 4.0tie11.5tie
- MCP Atlastie7676.4tie
ReasoningQwen3.7 Max
- SimpleBenchQwen3.7 Max by 12.557.970.4+12.5
- Humanity's Last ExamQwen3.7 Max by 5.53540.5+5.5
- CritPtQwen3.7 Max by 3.41013.4+3.4
- GPQA DiamondQwen3.7 Max by 2.789.692.3+2.7
- LiveBench · Reasoningtie82.883.3tie
FactsQwen3.7 Max
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 56.817.674.4+56.8
- SimpleQA VerifiedQwen3.7 Max by 19.336.555.8+19.3
- AA-Omniscience · AccuracyKimi K2.7 Code by 8.539.631.1+8.5
MathQwen3.7 Max
- FrontierMath Tier 4Qwen3.7 Max by 2212.234.1+22
- FrontierMath Tiers 1-3 (v2)Qwen3.7 Max by 10.65464.6+10.6
- LiveBench · MathematicsQwen3.7 Max by 5.779.685.3+5.7
Following instructionsQwen3.7 Max
- LiveBench · Instruction FollowingQwen3.7 Max by 17.756.374+17.7
- IFBenchQwen3.7 Max by 17.463.180.5+17.4
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.
- AA-OmniscienceQwen3.7 Max by 23.7-10.213.5+23.7
- MCPMarkKimi K2.7 Code by 20.381.160.8+20.3
- DeepSWE 1.1Kimi K2.7 Code by 9.43121.6+9.4
- livebench_data_analysisQwen3.7 Max by 9.162.771.8+9.1
- Artificial Analysis Coding IndexQwen3.7 Max by 5.260.866+5.2
- τ²-Bench Telecom (AA run)Qwen3.7 Max by 4.690.194.7+4.6
- AA IntelligenceQwen3.7 Max by 3.725.829.5+3.7
- MLS Bench Litelower is betterQwen3.7 Max by 3.435.131.7+3.4
- LiveBenchQwen3.7 Max by 2.471.974.3+2.4
- livebench_languageQwen3.7 Max by 1.877.979.7+1.8
- AA Agentic IndexQwen3.7 Max by 1.422.523.9+1.4
Questions people ask
Which is better, Kimi K2.7 Code or Qwen3.7 Max?
Qwen3.7 Max wins five of the seven areas where both have results: coding, reasoning, facts, math and following instructions. Kimi K2.7 Code wins none, but costs 51% less. They are level on agents and long documents.
Which is better for coding?
Qwen3.7 Max. It wins 4 of the 6 coding tests both models report; Kimi K2.7 Code wins 1, and 1 is a tie.
Which is cheaper?
Kimi K2.7 Code costs $0.95 per million input tokens and $4.00 per million output tokens; Qwen3.7 Max costs $2.50 and $7.50. That makes Kimi K2.7 Code about 51% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 24 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.