Benchmarks of JT Mini11
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Documents1
Legacy · saturated or no longer reported2
No benchmark matches
—per task?
API price not publicprice
—output speed?
128Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow×2.9—$0.005Function calling only with none · Chat Completions+3
OpenDeepSeek V4 Pro 0813max×3.5—$0.67Pass back reasoning_content · Chat Completions+4BetterGPT-5.6 Lunalow×2.8—$0.01
BetterNemotron 3 Nano 30B A3BthinkingOpen+22%—$0.017
BetterMistral Small 4thinkingOpen+53%—$0.017ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×2.9—$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2.8—$0.01Nemotron 3 Nano 30B A3BthinkingOpen+22%—$0.017Mistral Small 4thinkingOpen+53%—$0.017DeepSeek V3non-thinkingOpen+79%—$0.02ModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen×3.5—$0.67Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen×3.3—$2.00Sampling parameters are fixed+3DeepSeek V4.1 Flash 1017maxOpen×3—$0.26Pass back reasoning_content · Chat Completions+4TInklingxhighOpen×2.9—$0.60
Step 5 PreviewthinkingOpen×2.9—$1.03web_search not available · Chat Completions+2ModelScoreCostPer taskWhat changes
CJT-4.1 Flash 236B A21Bthinking×3.5——CJT 35B Flash+70%——All China Mobile models →Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam6.4#237
AA Omniscience Index-64.1#281
CritPt (physics)0#182
AA Intelligence Index 4.3.2≈12.2#181
AA Omniscience · Accuracy14.2#250
GPQA Diamond67.6#199
Coding
Agents & Tool Use
τ²-bench · AA93#30
Writing & Language
IFBench (instructions)36.7#175
FAQ
How much does JT Mini cost?›
There is no per-unit API price: API price not public.
Is JT Mini free to use?›
There is no free API.
How good is JT Mini, and what is it best at?›
#235 of 336 in Chat & Knowledge, #95 of 239 in Coding, #30 of 242 in Agents & Tool Use, #173 of 245 in Writing & Language. Strongest at: Tool calling.
Is JT Mini better than Granite 4.0 H Small?›
On AA Omniscience · Accuracy, JT Mini scores 14.2 vs 14.3 — about the same.
What is the context window of JT Mini?›
128K tokens.
When was JT Mini released? Is there a newer version?›
Released 2026-04-15. It is the current version in its line.
Is JT Mini open source?›
No, JT Mini is a closed model available through an API. The closest open-weights option here is DeepSeek V4 Pro 0813.
Can JT Mini read images?›
No, it accepts text only.
What is JT Mini?›
JT Mini is a closed language model from China Mobile, released Apr 2026.
What are the best alternatives to JT Mini?›
GPT-6 Luna (better), DeepSeek V4 Pro 0813 (open weights).