Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
0 benchmarks in common.
4 models selected. 0 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | Anthropic | Qwen | OpenAI | DeepSeek |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,470 | Not in our dataset | 1,390 | 1,458 |
| LiveBench 1.0General reasoning | Not in our dataset | 71.3% | Not in our dataset | 77.4% |
| GPQA DiamondScientific knowledge | Not in our dataset | 64.0% | 82.3% | 72.9% |
| HLEAcademic reasoning | 14.2% | Not in our dataset | 16.7% | 7.7% |
| MMLU ProMulti-task understanding | Not in our dataset | Not in our dataset | 83.7% | 82.9% |
| SimpleBenchCommonsense reasoning | Not in our dataset | Not in our dataset | Not in our dataset | 50.9% |
| AIME 2025Mathematics | Not in our dataset | 70.4% | 91.1% | Not in our dataset |
| GSOGraduate science | 26.5% | Not in our dataset | Not in our dataset | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | Not in our dataset | 72.0% | 73.6% |
| LiveCodeBenchCompetitive coding | Not in our dataset | 63.5% | 80.4% | 56.8% |
| Terminal-BenchAgentic terminal | Not in our dataset | Not in our dataset | 24.0% | Not in our dataset |
| ARC-AGI-2Visual reasoning | 7.8% | Not in our dataset | 4.4% | 0.8% |
Pricing & context Published USD rates per 1M tokens
| Specification | Claude Opus 4 4.5 Non-thinking | 3 14B Thinking | GPT-5 Mini Thinking (5.0) | V4 Pro |
|---|---|---|---|---|
| Input | $5 | $0.12 | $0.25 | $1.6 |
| Output | $25 | $0.24 | $2 | $3.2 |
| Context window | 200K | 41K | 400K | 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.