The Model Index
Up to four models

Kimi K2.5 vs Qwen 3.5 Plus (hosted 397B-A17B)

On the index (GPT-4 = 100), Kimi K2.5 scores 145 and Qwen 3.5 Plus (hosted 397B-A17B) 141. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Kimi K2.5
Presets
Kimi K2.5
145130–161
WeightsOpen
ReleasedJan 2026
Price in / out$0.50 / $2.5
Context262K
Core tests taken5 of 9
Qwen 3.5 Plus (hosted 397B-A17B)
141124–158
WeightsClosed
ReleasedFeb 2026
Price in / out–
Context–
Core tests taken1 of 9

Kimi K2.5 and Qwen 3.5 Plus (hosted 397B-A17B) are too close to call (4 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Kimi K2.5Qwen 3.5 Plus (hosted 397B-A17B)
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProCL-benchCL-benchSimpleQA VerifiedSimpleQA VerifiedMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1PROFESSIONAL WORKCorpFin v2CorpFin v2MortgageTaxMortgageTax
Every result as a table
TestKimi K2.5Qwen 3.5 Plus (hosted 397B-A17B)
Reasoning & knowledge
GPQA Diamond (Epoch AI)87.6%84.9%
GPQA Diamond (Vals AI)84.1%87.4%
MMLU Pro85.9%87.2%
MMMU Pro84.3%22.8%
CL-bench19.3%19.8%
SimpleQA Verified34.3%25.4%
Maths
AIME-style maths (OTIS mock)92.2%86.7%
FrontierMath (2025 set)27.9%21.0%
FrontierMath tier 4 (2025 set)4.2%2.1%
Coding
LiveCodeBench83.9%85.3%
SWE-bench70.0%71.2%
Vibe Code Bench v1.117.5%15.7%
Professional work
CorpFin v268.3%65.3%
MortgageTax66.5%60.8%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG