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 | NVIDIA | MiniMax | OpenAI | Anthropic |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,360 | Not in our dataset | 1,389 | 1,448 |
| GPQA DiamondScientific knowledge | Not in our dataset | 69.2% | Not in our dataset | Not in our dataset |
| HLEAcademic reasoning | 18.3% | 7.2% | Not in our dataset | 7.9% |
| MMLU ProMulti-task understanding | 83.7% | 80.6% | Not in our dataset | Not in our dataset |
| SimpleBenchCommonsense reasoning | Not in our dataset | Not in our dataset | 41.7% | Not in our dataset |
| AIME 2025Mathematics | Not in our dataset | 74.6% | Not in our dataset | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | 55.6% | Not in our dataset | Not in our dataset |
| Tau-BenchAgentic tool use | 62.8% | 67.8% | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | Nemotron 3 Super 120B-A12B | M1 Reasoning 40K | o1 Preview | Claude Opus 4 4.1 Non-thinking |
|---|---|---|---|---|
| Input | $0.3 | $0.55 | $15 | $15 |
| Output | $2.4 | $2.2 | $60 | $75 |
| Context window | 1.0M | 1.0M | 200K | 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.