Kimi K2 ThinkingvsQwen3.7-Max

Kimi K2 Thinking
Qwen3.7-Max
Specifications
Parameters
1T
Context window
256k
API pricing
Input price
$2.50
Output price
$7.50
Cheapest input
$0.60Google
Cheapest output
$2.50Google
Benchmarks
SWE-Bench Verified
71.3%80.4%
Benchmarks
BullshitBench v2
71%
SWE-Bench Pro
60.6%
LiveCodeBench
91.6%
Terminal-Bench 2.0
69.7%
MCP Atlas
76.4%
Humanity's Last Exam · with tools
41.4%
GPQA Diamond
92.4%
Overview
CompanyMoonshot AIQwen
Release dateNov 6 2025May 20 2026
AccessOpen WeightProprietary

Other comparisons

Kimi K2 ThinkingvsClaude Opus 5Qwen3.7-MaxvsClaude Opus 5Kimi K2 ThinkingvsGPT-5.6 SolQwen3.7-MaxvsGPT-5.6 SolKimi K2 ThinkingvsGemini 3.7 FlashQwen3.7-MaxvsGemini 3.7 FlashKimi K2 ThinkingvsMuse GlimmerQwen3.7-MaxvsMuse GlimmerKimi K2 ThinkingvsGrok 4.6Qwen3.7-MaxvsGrok 4.6Kimi K2 ThinkingvsDeepSeek-V4-Pro-0813Qwen3.7-MaxvsDeepSeek-V4-Pro-0813

Frequently asked questions

Qwen3.7-Max leads Kimi K2 Thinking on 1 of the 1 benchmark they both report (SWE-Bench Verified). Only Qwen3.7-Max has a verified first-party API price: $2.50 per million input tokens and $7.50 per million output tokens. No pay-as-you-go API rate is tracked for Kimi K2 Thinking. Kimi K2 Thinking shipped 195 days before Qwen3.7-Max, so benchmark comparisons should account for the intervening progress.

Kimi K2 Thinking is open weight, while Qwen3.7-Max is proprietary.

On SWE-Bench Verified, Qwen3.7-Max leads at 80.4% vs Kimi K2 Thinking at 71.3%.

Kimi K2 Thinking was released by Moonshot AI on Nov 6 2025.

Qwen3.7-Max was released by Qwen on May 20 2026.

Qwen3.7-Max leads on SWE-Bench Verified — Kimi K2 Thinking 71.3% vs Qwen3.7-Max 80.4%.

Only Qwen3.7-Max has a verified first-party API price: $2.50 per million input tokens and $7.50 per million output tokens. No pay-as-you-go API rate is tracked for Kimi K2 Thinking. Rates are pay-as-you-go API prices verified on August 18, 2026.

Kimi K2 Thinking is an open weight model released by Moonshot AI. Qwen3.7-Max is a proprietary model released by Qwen.