Providers do have offers, but we have not collected a current price yet. That is a gap on our side, not a model missing from the market.
| Task set | Result | Run conditions | Measured by |
|---|---|---|---|
| Arena Score in English | 1,256.17 1,247–1,265 | — | — |
| Arena Score, overall | 1,248.54 1,241–1,256 | — | — |
| Arena Score in Russian | 1,248.3 1,230–1,266 | — | — |
| Arena Score, creative writing | 1,236.64 1,219–1,255 | — | — |
| Arena Score, programming | 1,230.51 1,215–1,246 | — | — |
| Arena Score, multi-turn dialogue | 1,226.63 1,210–1,243 | — | — |
| Arena Score, mathematics | 1,221.72 1,207–1,236 | — | — |
| Arena Score, long queries | 1,220.62 1,202–1,239 | — | — |
| Arena Score, expert questions | 1,213.1 1,188–1,238 | — | — |
| Arena Score, instruction following | 1,212.35 1,202–1,222 | — | — |
| Arena Score, hard prompts | 1,211.26 1,200–1,223 | — | — |