Kimi K2.5 vs Qwen3.7 Max
Wins 0 of 7 areas
—
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
Qwen3.7 Max is the stronger all-rounder.Kimi K2.5 is cheaper.
Scores updated · 36 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 software07Qwen3.7 Max7 of 8 tests · 1 tie
- ReasoningHard problems that need careful thinking03Qwen3.7 Max3 of 3 tests
- MathCompetition and research-level math03Qwen3.7 Max3 of 3 tests
- AgentsCarrying out multi-step tasks on its own12Qwen3.7 Max2 of 3 tests
- FactsGetting facts right instead of making them up12Qwen3.7 Max2 of 3 tests
- Long documentsFinding answers in very long texts01Qwen3.7 Max1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.7 Max1 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.
Kimi K2.5 costs 64% 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 Max pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+40.1points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+28.8points ahead
- Short factual questions, answered correctlySimpleQA Verified+21.5points ahead
Where Kimi K2.5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+4.1points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+2.4points ahead
Every test, side by side
All 36 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 28.845.774.5+28.8
- Terminal-Bench HardQwen3.7 Max by 1634.850.8+16
- SWE-bench ProQwen3.7 Max by 9.950.760.6+9.9
- LMArena · WebDevQwen3.7 Max by 79 rating points14361515+79 rating
- LiveCodeBench v6Qwen3.7 Max by 6.68591.6+6.6
- SWE-bench MultilingualQwen3.7 Max by 5.37378.3+5.3
- SWE-bench VerifiedQwen3.7 Max by 3.676.880.4+3.6
- SciCodetie4949.5tie
AgentsQwen3.7 Max
- GDPValQwen3.7 Max by 14.417.231.6+14.4
- MCP AtlasQwen3.7 Max by 12.663.876.4+12.6
- τ-Bench V3 · BankingKimi K2.5 by 2.414.211.8+2.4
ReasoningQwen3.7 Max
- CritPtQwen3.7 Max by 10.33.113.4+10.3
- Humanity's Last ExamQwen3.7 Max by 9.830.740.5+9.8
- GPQA DiamondQwen3.7 Max by 4.487.992.3+4.4
FactsQwen3.7 Max
- AA-Omniscience · Non-hallucinationQwen3.7 Max by 40.134.374.4+40.1
- SimpleQA VerifiedQwen3.7 Max by 21.534.355.8+21.5
- AA-Omniscience · AccuracyKimi K2.5 by 4.135.231.1+4.1
MathQwen3.7 Max
- HMMT Feb. 2026Qwen3.7 Max by 1087.197.1+10
- IMOAnswerBenchQwen3.7 Max by 8.281.890+8.2
- AIME 2026Qwen3.7 Max by 1.295.897+1.2
Following instructionsQwen3.7 Max
- IFBenchQwen3.7 Max by 10.370.280.5+10.3
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.
- MCPMarkQwen3.7 Max by 31.329.560.8+31.3
- AA-OmniscienceQwen3.7 Max by 20.8-7.313.5+20.8
- Artificial Analysis Coding IndexQwen3.7 Max by 19.246.866+19.2
- Terminal-Bench 2.0Qwen3.7 Max by 18.950.869.7+18.9
- NL2RepoQwen3.7 Max by 15.23247.2+15.2
- AA IntelligenceQwen3.7 Max by 623.529.5+6
- HMMT Nov. 2025Qwen3.7 Max by 5.889.295+5.8
- LiveBenchQwen3.7 Max by 5.269.174.3+5.2
- WideSearchKimi K2.5 by 3.87975.2+3.8
- HLE (with tools)Qwen3.7 Max by 3.350.253.5+3.3
- MMLU-ProQwen3.7 Max by 2.587.189.6+2.5
- AA Agentic IndexQwen3.7 Max by 2.221.723.9+2.2
- PaperBenchQwen3.7 Max by 1.363.564.8+1.3
- τ²-Bench Telecom (AA run)Kimi K2.5 by 1.295.994.7+1.2
Questions people ask
Which is better, Kimi K2.5 or Qwen3.7 Max?
Qwen3.7 Max wins all seven areas where both have results: coding, agents, reasoning, facts, math, long documents and following instructions. Kimi K2.5 wins none, but costs 64% less.
Which is better for coding?
Qwen3.7 Max. It wins 7 of the 8 coding tests both models report; Kimi K2.5 wins none, and 1 is a tie.
Which is cheaper?
Kimi K2.5 costs $0.60 per million input tokens and $3.00 per million output tokens; Qwen3.7 Max costs $2.50 and $7.50. That makes Kimi K2.5 about 64% cheaper for the same work.
How do you compare the two?
We use the 36 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 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.