Instruction following
Whether the model obeys explicit constraints on its output — format, length, inclusions, exclusions — independently of whether the content is any good.
Ordered by how many of these benchmarks put a model in their top 10, then by its best placing. Each column keeps its own ranking; nothing is averaged.
| Model | In top 10 | Artificial Analysis LLM Leaderboard IFBench |
|---|---|---|
 Grok 4.3 xai | 1/1 | #1 83.3% |
| Grok 4.20 xai | 1/1 | #2 82.9% |
 MiniMax M3 minimax | 1/1 | #3 82.9% |
 Nemotron 3 Ultra nvidia | 1/1 | #4 81.4% |
 Qwen 3.7 Max alibaba | 1/1 | #5 80.5% |
| Nemotron Cascade 2 nvidia | 1/1 | #6 80.4% |
 MiMo V2.5 Pro xiaomi | 1/1 | #7 79.9% |
 Nova 2.0 Pro aws | 1/1 | #8 79.6% |
 DeepSeek V4 Flash deepseek | 1/1 | #9 79.2% |
| Qwen 3.5 alibaba | 1/1 | #10 78.8% |
A dash means the board does not list that model — not a score of zero. Entries not yet matched to a model are left out here; they still appear on their own board.