Benchmarks of JT 35B Flash11
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Documents1
Legacy · saturated or no longer reported2
No benchmark matches
—per task?
API price not publicprice
—output speed?
256Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow+69%—$0.005Function calling only with none · Chat Completions+3
OpenDeepSeek V4 Pro 0813max×2—$0.67Pass back reasoning_content · Chat Completions+4BetterGPT-5.6 Lunalow+64%—$0.01
BetterClaude Haiku 5.5low+37%—$0.024Remove sampling parameters+5BetterGPT-6.1 Terralow+97%—$0.055ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow+69%—$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+64%—$0.01Claude Haiku 5.5low+37%—$0.024Remove sampling parameters+5GPT-6.1 Terralow+97%—$0.055
Muse Glimmer 30BhighOpen+12%—$0.058Context: 256K → 131KModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen×2—$0.67Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen+97%—$2.00Sampling parameters are fixed+3DeepSeek V4.1 Flash 1017maxOpen+77%—$0.26Pass back reasoning_content · Chat Completions+4TInklingxhighOpen+72%—$0.60
Step 5 PreviewthinkingOpen+72%—$1.03web_search not available · Chat Completions+2ModelScoreCostPer taskWhat changes
CJT-4.1 Flash 236B A21Bthinking×2——CJT Mini-41%——Context: 256K → 128KAll China Mobile models →Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam6.4#237
AA Omniscience Index-24.2#138
CritPt (physics)0#182
AA Intelligence Index 4.3.2≈18.7#128
AA Omniscience · Accuracy24.2#126
AA-LCR (long context) 1.165.7#139
GPQA Diamond82.9#97
Coding
Agents & Tool Use
τ²-bench · AA99.1#1
Writing & Language
IFBench (instructions)42#144
FAQ
How much does JT 35B Flash cost?›
There is no per-unit API price: API price not public.
Is JT 35B Flash free to use?›
There is no free API.
How good is JT 35B Flash, and what is it best at?›
#235 of 336 in Chat & Knowledge, #62 of 239 in Coding, #1 of 242 in Agents & Tool Use, #143 of 245 in Writing & Language. Strongest at: Tool calling.
Is JT 35B Flash better than Qwen3 Max (Preview)?›
On AA Omniscience · Accuracy, JT 35B Flash scores 24.2 vs 24.2 — about the same.
What is the context window of JT 35B Flash?›
256K tokens.
When was JT 35B Flash released? Is there a newer version?›
Released 2026-05-14. It is the current version in its line.
Is JT 35B Flash open source?›
No, JT 35B Flash is a closed model available through an API. The closest open-weights option here is DeepSeek V4 Pro 0813.
Can JT 35B Flash read images?›
No, it accepts text only.
What is JT 35B Flash?›
JT 35B Flash is a closed language model from China Mobile, released May 2026.
What are the best alternatives to JT 35B Flash?›
GPT-6 Luna (better), DeepSeek V4 Pro 0813 (open weights).