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 | Qwen | xAI | OpenAI | Anthropic |
|---|---|---|---|---|
| Arena ELOHuman preference | Not in our dataset | 1,411 | 1,401 | Not in our dataset |
| LiveBench 1.0General reasoning | 67.1% | Not in our dataset | 69.6% | Not in our dataset |
| GPQA DiamondScientific knowledge | 62.0% | 80.2% | 82.8% | 73.0% |
| HLEAcademic reasoning | Not in our dataset | Not in our dataset | 24.3% | 9.7% |
| SimpleBenchCommonsense reasoning | Not in our dataset | 36.1% | Not in our dataset | Not in our dataset |
| AIME 2025Mathematics | 67.3% | 77.3% | Not in our dataset | 80.7% |
| AiderCode editing | Not in our dataset | 53.3% | Not in our dataset | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | Not in our dataset | Not in our dataset | 73.3% |
| LiveCodeBenchCompetitive coding | 57.5% | 70.6% | Not in our dataset | 53.2% |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | Not in our dataset | 83.2% |
| ARC-AGI-2Visual reasoning | Not in our dataset | 0.0% | 5.7% | 4.0% |
Pricing & context Published USD rates per 1M tokens
| Specification | 3 8B Thinking | Grok 3 Thinking | GPT-5 Nano Thinking (5.4) | Claude Haiku 4.5 Thinking |
|---|---|---|---|---|
| Input | $0.117 | $3 | $0.05 | $1 |
| Output | $0.455 | $15 | $0.4 | $5 |
| Context window | 131K | 131K | 400K | 200K |
| 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.