Best for Agents & Tool Use
Agents & Tool Use benchmarks83
BenchmarkByLeaderModels
Agents28
Health & law1
Documents1
Reported by labs40
Legacy · saturated or no longer reported13
No benchmark matches
| Model | BFCL v4 (past run, prompt mode) | Per task | Price | Speed | Supports | Context |
|---|---|---|---|---|---|---|
50.9unstated | — | $0.30 / $2.50 | — | 1M | ||
46.8unstated | — | $0.70 / $2.80 | — | 33K | ||
45.3unstated | — | $1.75 / $14 | — | 400K | ||
40.4unstated | — | $0.18 / $0.70 | — | 33K | ||
39.4 | — | $2 / $8 | — | 1M | ||
37.8unstated | — | $0.35 / $1.40 | — | 33K | ||
36.7unstated | — | $0.09 / $0.30 | — | 262K | ||
35.5unstated | — | $0.40 / $0.80 | — | 262K | ||
33.5unstated | — | $5 / $25 | — | 200K | ||
29.7 | — | $0.40 / $1.60 | — | 1M | ||
28unstated | — | $0.10 / $0.40 | — | 1M | ||
27.8unstated | — | $0.25 / $2 | — | 400K | ||
27.6unstated | — | $0.05 / $0.40 | — | 400K | ||
25.3unstated | — | $1 / $5 | — | 200K | ||
24.9unstated | — | $3 / $15 | — | 1M | ||
22.4unstated | — | $0.04 / $0.08 | — | 33K |