Best for Chat & Knowledge
Chat & Knowledge benchmarks143
BenchmarkByLeaderModels
Overall1
Knowledge24
Reasoning9
Math54
Science6
Health & law6
Documents2
Reported by labs36
Legacy · saturated or no longer reported5
No benchmark matches
| Model | FrontierMath Tier 4 | Per task | Price | Speed | Supports | Context |
|---|---|---|---|---|---|---|
31.3max | $4.08 | $5 / $25 | 66 | 1M | ||
27.1xhigh | — | $2.50 / $15 | — | 1.05M | ||
22.9xhigh | — | $5 / $25 | — | 1M | ||
22.9max | — | $5 / $25 | 48 | 1M | ||
18.8xhigh | — | $1.75 / $14 | — | 400K | ||
16.7unstated | — | $2 / $12 | — | 1M | ||
14.6unstated | — | $1.25 / $4.25 | — | 1M | ||
14.6 | — | $15 / $120 | — | 400K | ||
14.6unstated | — | $0.95 / $4 | — | 256K | ||
12.5unstated | — | $1.40 / $4.40 | — | 203K | ||
12.5high | — | $1.25 / $10 | — | 400K | ||
12.5high | — | $1.25 / $10 | — | 400K | ||
8.3unstated | — | $0.50 / $3 | — | 1M | ||
6.3high | — | $0.25 / $2 | — | 400K | ||
6.3high | — | $0.20 / $1.25 | — | 400K | ||
4.2unstated | — | $5 / $25 | — | 200K | ||
4.2unstated | — | $0.30 / $2.50 | — | 1M | ||
4.2unstated | — | $1.25 / $10 | — | 1M | ||
4.2unstated | — | $0.50 / $3 | — | 1M | ||
4.2unstated | — | $1.30 / $7.80 | — | 262K | ||
2.1unstated | — | $0.60 / $2.20 | — | 200K | ||
2.1unstated | — | $1 / $3.20 | — | 203K | ||
2.1unstated | — | $3 / $15 | — | 1M | ||
2.1medium | — | $0.05 / $0.40 | — | 400K | ||
2.1high | — | $2 / $8 | — | 200K | ||
2.1unstated | — | $0.12 / $0.69 | — | 1M | ||
2.1high | — | $0.75 / $4.50 | — | 400K | ||
0unstated | — | $0.47 / $2 | — | 256K | ||
0unstated | — | $0.23 / $2.30 | — | 262K | ||
0unstated | — | $0.065 / $0.26 | — | 1M | ||
0unstated | — | $0.25 / $1.50 | — | 1M | ||
0unstated | — | $0.60 / $2.20 | — | 203K | ||
0 | — | $2 / $8 | — | 1M |