INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...
text->text| Provider | Region / Tag | Context | Input/M | Output/M | Uptime 1d | Latency | Quant | Cache |
|---|---|---|---|---|---|---|---|---|
| Nebius | nebius/fp8 | 131K | $0.200 | $1.10 | 100.00% | - | fp8 | - |
| Rank | Category | Variant | Trend | Elo | Votes |
|---|---|---|---|---|---|
| #135 | Math | - | 1384 | 332 | |
| #136 | Industry Mathematical | - | 1385 | 233 | |
| #145 | Hard Prompts English | - | 1399 | 1,433 | |
| #146 | English | - | 1385 | 2,615 | |
| #151 | Coding | - | 1409 | 973 | |
| #151 | Multi Turn | - | 1359 | 780 | |
| #152 | Industry Business And Management And Financial Operations | - | 1363 | 985 | |
| #152 | Industry Software And It Services | - | 1400 | 1,711 | |
| #154 | Chinese | - | 1382 | 293 | |
| #158 | Hard Prompts | - | 1373 | 2,741 | |
| #159 | Exclude Ties | - | 1318 | 3,801 | |
| #159 | Overall | - | 1356 | 5,329 | |
| #160 | Industry Writing And Literature And Language | - | 1337 | 1,268 | |
| #163 | Expert | - | 1354 | 309 | |
| #163 | Industry Life And Physical And Social Science | - | 1368 | 890 | |
| #167 | Longer Query | - | 1352 | 1,262 | |
| #169 | Russian | - | 1331 | 449 | |
| #171 | Creative Writing | - | 1312 | 800 | |
| #174 | Industry Entertainment And Sports And Media | - | 1305 | 1,064 | |
| #174 | Instruction Following | - | 1330 | 1,393 | |
| #204 | Industry Medicine And Healthcare | - | 1333 | 315 | |
| #209 | Industry Legal And Government | - | 1328 | 398 |