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 | Anthropic | Zhipu AI | Qwen | MiniMax |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,448 | 1,411 | Not in our dataset | Not in our dataset |
| GPQA DiamondScientific knowledge | Not in our dataset | Not in our dataset | 73.4% | 69.2% |
| HLEAcademic reasoning | 7.9% | 8.3% | 9.8% | 7.2% |
| MMLU ProMulti-task understanding | Not in our dataset | Not in our dataset | 80.9% | 80.6% |
| AIME 2025Mathematics | Not in our dataset | Not in our dataset | 85.0% | 74.6% |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | Not in our dataset | 22.0% | 55.6% |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | Not in our dataset | 67.8% |
Pricing & context Published USD rates per 1M tokens
| Specification | Claude Opus 4 4.1 Non-thinking | GLM-4 4.5 | 3 30B A3B Thinking (2507) | M1 Reasoning 40K |
|---|---|---|---|---|
| Input | $15 | $0.6 | $0.12 | $0.55 |
| Output | $75 | $2.2 | $0.5 | $2.2 |
| Context window | 200K | 131K | 41K | 1.0M |
| 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.