AI21 Labs model product
State-of-the-art hybrid SSM-Transformer instruction following foundation model, offering superior long context handling, speed, and quality.
Updated Aug 10, 2026. Default version: Jamba 1.5 Large
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version Jamba 1.5 Large.
| ARC-C | 0.9 | 7 | 34 | 81.8% | C | |
| Wild Bench | 0.5 | 7 | 8 | 14.3% | C | |
| TruthfulQA | 0.6 | 9 | 18 | 52.9% | C | |
| Arena Hard | 0.7 | 12 | 26 | 56.0% | C | |
| GSM8k | 0.9 | 33 | 48 | 31.9% | C | |
| MMLU | 0.8 | 53 | 100 | 47.5% | C | |
| MMLU-Pro | 0.5 | 110 | 129 | 14.8% | C | |
| GPQA | 0.4 | 209 | 233 | 10.3% | C |
Preference and agent-evaluation signals from published Arena datasets.
| text style control | japanese | 212 | 1177.8 | 242 | N/A | |
| text | japanese | 215 | 1118.6 | 242 | N/A | |
| text style control | german | 230 | 1253.2 | 234 | N/A | |
| text | german | 231 | 1199.7 | 234 | N/A | |
| text style control | industry legal and government | 243 | 1325.7 | 448 | N/A | |
| text style control | expert | 246 | 1283.4 | 331 | N/A | |
| text style control | industry entertainment and sports and media | 246 | 1270.6 | 1,433 | N/A | |
| text | expert | 247 | 1216.9 | 331 | N/A | |
| text | industry legal and government | 252 | 1264.2 | 448 | N/A | |
| text style control | creative writing | 259 | 1261.1 | 1,379 | N/A | |
| text style control | industry life and physical and social science | 259 | 1313.8 | 1,358 | N/A | |
| text style control | industry writing and literature and language | 260 | 1276.4 | 2,350 | N/A | |
| text | industry entertainment and sports and media | 261 | 1218.8 | 1,433 | N/A | |
| text style control | english | 261 | 1315.5 | 4,915 | N/A | |
| text style control | overall | 262 | 1289.2 | 8,662 | N/A | |
| text style control | exclude ties | 263 | 1213.5 | 5,535 | N/A | |
| text | industry life and physical and social science | 264 | 1249.8 | 1,358 | N/A | |
| text | industry mathematical | 264 | 1227.5 | 962 | N/A | |
| text | english | 265 | 1266.8 | 4,915 | N/A | |
| text style control | industry medicine and healthcare | 266 | 1281.9 | 474 | N/A | |
| text | overall | 267 | 1237.2 | 8,662 | N/A | |
| text | exclude ties | 267 | 1139.9 | 5,535 | N/A | |
| text | industry writing and literature and language | 267 | 1227.7 | 2,350 | N/A | |
| text | instruction following | 267 | 1213.0 | 3,266 | N/A | |
| text | math | 267 | 1221.1 | 1,147 | N/A | |
| text style control | chinese | 267 | 1276.2 | 675 | N/A | |
| text style control | industry software and it services | 267 | 1310.0 | 2,339 | N/A | |
| text | hard prompts english | 268 | 1232.9 | 1,528 | N/A | |
| text style control | coding | 268 | 1312.2 | 1,440 | N/A | |
| text style control | industry mathematical | 268 | 1257.3 | 962 | N/A | |
| text | creative writing | 269 | 1212.1 | 1,379 | N/A | |
| text style control | instruction following | 269 | 1266.4 | 3,266 | N/A | |
| text | industry medicine and healthcare | 270 | 1195.7 | 474 | N/A | |
| text | industry software and it services | 270 | 1237.5 | 2,339 | N/A | |
| text style control | hard prompts | 270 | 1283.6 | 2,372 | N/A | |
| text style control | hard prompts english | 270 | 1294.9 | 1,528 | N/A | |
| text style control | multi turn | 270 | 1266.1 | 1,634 | N/A | |
| text | hard prompts | 271 | 1218.0 | 2,372 | N/A | |
| text | chinese | 272 | 1202.1 | 675 | N/A | |
| text | multi turn | 272 | 1219.9 | 1,634 | N/A | |
| text style control | math | 272 | 1244.9 | 1,147 | N/A | |
| text | coding | 273 | 1228.0 | 1,440 | N/A | |
| text style control | industry business and management and financial operations | 274 | 1264.4 | 979 | N/A | |
| text style control | non english | 274 | 1251.8 | 3,747 | N/A | |
| text style control | russian | 275 | 1251.1 | 998 | N/A | |
| text | russian | 276 | 1194.9 | 998 | N/A | |
| text | industry business and management and financial operations | 277 | 1196.0 | 979 | N/A | |
| text | non english | 280 | 1196.1 | 3,747 | N/A | |
| text | longer query | 281 | 1206.6 | 1,024 | N/A | |
| text style control | longer query | 288 | 1260.8 | 1,024 | N/A |
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
The default version has no provider offering with current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Jamba 1.5 Large | 38.3 | 398B | 256K | 256K | No | Jamba Open Model License |
A concise description based on the published model registry.
State-of-the-art hybrid SSM-Transformer instruction following foundation model, offering superior long context handling, speed, and quality.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Jamba 1.5 Large.
Jamba 1.5 Large's default version was released on Aug 22, 2024.
No official standard PAYG price is currently available for Jamba 1.5 Large.
Jamba 1.5 Large is published under AI21 Labs in the model registry.
The default version has a 256K token context window.
No. The default version is not marked as having publicly available weights.
No published provider offering is currently linked to the default version.
Nearby ranked alternatives include Claude Sonnet 3, Qwen3 30B A3B, Gemma 3 12B.