Up to four models
Gemini 3.5 Flash-Lite vs GLM-4.7
On the index (GPT-4 = 100), Gemini 3.5 Flash-Lite scores 141 and GLM-4.7 140. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
141125–156
WeightsClosed
ReleasedJul 2026
Price in / out$0.30 / $2.5
Context1.05M
Core tests taken5 of 9
140123–157
WeightsOpen
ReleasedDec 2025
Price in / out$0.40 / $1.75
Context205K
Core tests taken1 of 9
Gemini 3.5 Flash-Lite and GLM-4.7 are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests, at a similar price.
Test by testthird-party results
Every result as a table
| Test | Gemini 3.5 Flash-Lite | GLM-4.7 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 83.3% | 83.3% |
| GPQA Diamond (Vals AI) | 83.8% | 80.0% |
| MMLU Pro | 85.8% | 82.7% |
| Maths | ||
| AIME-style maths (OTIS mock) | 71.1% | 83.3% |
| Chess puzzles | 21.0% | 21.0% |
| Coding | ||
| LiveCodeBench | 79.0% | 82.2% |
| SWE-bench | 75.0% | 69.4% |
| Professional work | ||
| CorpFin v2 | 60.7% | 46.4% |
| LegalBench | 84.1% | 83.4% |
| MedCode | 43.5% | 32.8% |
| MedScribe | 70.9% | 68.6% |
| TaxEval v2 | 72.6% | 68.8% |
Tests at least two of these models have taken. Bold rows are the core tests.