Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
1 benchmarks in common.
4 models selected. 1 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | Zhipu AI | Google | Google | Google |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,441 | 1,456 | 1,458 | 1,445 |
| LiveBench 1.0General reasoning | Not in our dataset | 63.9% | Not in our dataset | 82.4% |
| GPQA DiamondScientific knowledge | 85.7% | Not in our dataset | Not in our dataset | 86.4% |
| HLEAcademic reasoning | 24.8% | Not in our dataset | Not in our dataset | 21.6% |
| MMLU ProMulti-task understanding | Not in our dataset | Not in our dataset | Not in our dataset | 86.0% |
| SimpleBenchCommonsense reasoning | 47.7% | Not in our dataset | Not in our dataset | 62.4% |
| AIME 2025Mathematics | Not in our dataset | Not in our dataset | Not in our dataset | 88.0% |
| GSOGraduate science | Not in our dataset | Not in our dataset | Not in our dataset | 3.9% |
| AiderCode editing | Not in our dataset | Not in our dataset | Not in our dataset | 83.1% |
| SWE-Bench VerifiedAgentic coding | 73.8% | Not in our dataset | Not in our dataset | 59.6% |
| LiveCodeBenchCompetitive coding | Not in our dataset | Not in our dataset | Not in our dataset | 70.4% |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | Not in our dataset | 67.0% |
| Terminal-BenchAgentic terminal | 41.0% | Not in our dataset | Not in our dataset | 32.6% |
| ARC-AGI-2Visual reasoning | Not in our dataset | 10.3% | Not in our dataset | 4.9% |
Pricing & context Published USD rates per 1M tokens
| Specification | GLM-4 4.7 | Gemini 3.5 Flash Lite | Gemini 3 Flash Preview | Gemini 2.5 Pro |
|---|---|---|---|---|
| Input | $0.6 | $0.3 | $0.5 | $1.25 |
| Output | $2.2 | $2.5 | $3 | $10 |
| Context window | 205K | 1.0M | Not available | Not available |
| Pricing details | Explore pricing → | Explore pricing → | Explore pricing → | Explore pricing → |
How to read this comparison
Each column keeps the exact model version you selected. Shared benchmarks are the intersection of their reported results; “all coverage” also shows where evidence is missing. Missing results never count as zero.
These are published benchmark scores, not a controlled head-to-head test. The available evidence does not establish matching evaluation settings, so we show no cross-model winner highlights or deltas. Composite quality scores are omitted because they can summarize different benchmark sets.
Scores and statistics are computed upstream. This page reads a fixed data snapshot; its date describes the snapshot, not the date of every measurement.