Chinese-developed multilingual (English, Chinese and others) model by 01.ai that's very fast and cheap, yet scores high on independent leaderboards.
Added Jun 15, 2025
Context Window
12.0K
Max Output
4.1K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$0.20/1M
Cache Read (Auto)
$0.10/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from LMArena.
Arena Score
1328.3
Overall Rank
#223 / 389
Votes
27,332
Confidence Interval
1323.4 - 1333.3
Category Scores
Coding
#221 / 384
4,316 votes
1369.2
Math
#217 / 374
3,921 votes
1305.0
Longer Query
#234 / 367
3,634 votes
1324.9
Creative Writing
#220 / 387
3,781 votes
1296.6
Instruction Following
#232 / 389
10,932 votes
1308.5
Hard Prompts
#219 / 389
6,961 votes
1341.1
Additional Categories21
Japanese
#171 / 256
565 votes
1254.3
Spanish
#182 / 272
341 votes
1337.5
French
#190 / 271
270 votes
1339.8
Industry Legal And Government
#191 / 361
1,697 votes
1364.9
Chinese
#199 / 360
2,736 votes
1362.0
Industry Medicine And Healthcare
#203 / 357
1,451 votes
1354.6
German
#206 / 293
700 votes
1292.5
Expert
#208 / 339
1,533 votes
1330.8
Multi Turn
#208 / 387
4,748 votes
1330.2
Industry Life And Physical And Social Science
#210 / 387
4,822 votes
1353.4
Industry Mathematical
#214 / 368
3,206 votes
1316.0
Korean
#214 / 264
425 votes
1224.8
English
#215 / 389
13,650 votes
1354.2
Hard Prompts English
#215 / 388
3,939 votes
1360.5
Industry Entertainment And Sports And Media
#216 / 387
3,980 votes
1294.5
Industry Software And It Services
#218 / 389
7,070 votes
1360.1
Exclude Ties
#221 / 389
17,462 votes
1280.7
Industry Business And Management And Financial Operations
#224 / 382
3,420 votes
1318.4
Industry Writing And Literature And Language
#232 / 388
7,632 votes
1302.7
Non English
#237 / 389
13,682 votes
1297.9
Russian
#253 / 352
4,189 votes
1285.6
Published 2026-08-12 · Matched as yi-lightning
LMArena DatasetProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Yi Lightning with similar models from the same provider or model family.
Yi Large
yi-largeLarge version of Yi Lightning with a 32k context window, but more expensive.
Yi Medium 200k
yi-medium-200kMedium version of Yi with a 200k context window.
Nvidia Nemotron 3.5 Lightning
nvidia/nemotron-3.5-lightningNvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant. Included in the NanoGPT subscription.
Nvidia Nemotron 3.5 Lightning Thinking
nvidia/nemotron-3.5-lightning:thinkingNvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. This variant enables its reasoning trace. Included in the NanoGPT subscription.
Gemma 4 31B MeroMero v2
Gemma-4-31B-MeroMero-v2Gemma 4 31B MeroMero v2 is a LoRA finetune for emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.
Ornith 1.5 9B
ornith-ai/ornith-1.5-9bOrnith 1.5 9B is an FP8 dense open-weight reasoning model built for agentic coding, tool use, visual understanding, and efficient long-context work.