Up to four models
GLM-4.7 vs Kimi K2 Thinking
On the index (GPT-4 = 100), GLM-4.7 scores 140 and Kimi K2 Thinking 139. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
140123–157
WeightsOpen
ReleasedDec 2025
Price in / out$0.40 / $1.75
Context205K
Core tests taken1 of 9
Kimi K2 Thinking
139123–156
WeightsOpen
ReleasedNov 2025
Price in / out$0.60 / $2.5
Context262K
Core tests taken2 of 9
GLM-4.7 and Kimi K2 Thinking are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests, and costs 1.5× less.
Test by testthird-party results
Every result as a table
| Test | GLM-4.7 | Kimi K2 Thinking |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 83.3% | 84.2% |
| CL-bench | 15.9% | 17.6% |
| SimpleBench | 47.7% | 39.6% |
| Maths | ||
| AIME-style maths (OTIS mock) | 83.3% | 83.1% |
| FrontierMath (2025 set) | 2.4% | 21.4% |
| FrontierMath tier 4 (2025 set) | 0.0% | 0.0% |
| Coding | ||
| Terminal-Bench 2.0 (Terminus 2 runs) | 33.4% | 35.7% |
Task length · METR36 sec
Tests at least two of these models have taken. Bold rows are the core tests.