JT-4.1 Flash 236B A21B
JT-4.1 Flash 236B A21B is a China Mobile proprietary reasoning model, released 9 Jul 2026. Its best configuration (no reasoning reasoning effort) ranks #331 of 785 on the BenchLeader Index at 52.0 ±6.9, in the upper half. The ± is the point: 389 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (61) and lowest in reasoning (41). It has been measured at 2 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 9 Jul 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 262k
- Full answer
- –
- Cost per run
- –
- Released
- 9 Jul 2026
- Overall index52
- Reasoning41
- Knowledge58
- Multimodal47
- Long context61
- Composite60
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoningbest | 52.0 | #331 | – | – | – | Composite 60 · Knowledge 58 · Long context 61 · Multimodal 47 · Reasoning 41 |
| thinking | – | – | – | – | – | Composite 67 · Knowledge 71 · Long context 64 · Reasoning 64 |
How its index has moved
2 Oct 2026 to 18 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| GPQA Diamond (AA)not in index | 84.5%#137 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 17.8%#234 | 43.6%#57 | Artificial Analysis | |
| CritPt | 0.0%#315 | 14.0%#100 | Artificial Analysis |
Coding
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| SciCode (AA)not in index | – | 52.0%#89 | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | – | 3.0%#108 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 59.5%#100 | – | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| GDPval-AA v2.1not in index | 31.1%#79 | 41.1%#61 | Artificial Analysis | |
| AutomationBenchnot in index | – | 46.5%#90 | Artificial Analysis | |
| GDP.pdf (AA)not in index | – | 8.6%#140 | Artificial Analysis |
Knowledge
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| AA-Omniscience | -8.8#182 | 20.6#66 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 24.3%#248 | 49.4%#66 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 56.3%#88 | 43.0%#149 | Artificial Analysis |
Multimodal
| Benchmark | no reasoning | Source | Trend |
|---|---|---|---|
| MMMU-Pro | 64.1%#186 | Artificial Analysis |
Long context
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| AA-LCR | 71.3%#203 | 78.3%#112 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| AA Intelligence Index v4.3.2 | 27.3#144 | 33.9#100 | Artificial Analysis |
More from China Mobile
See also
Questions people ask
- What are JT-4.1 Flash 236B A21B's benchmark scores?
- As of 25 Oct 2026, JT-4.1 Flash 236B A21B (no reasoning effort) scores 52.0 ±6.9 on the BenchLeader Index, strongest in long context (61) and weakest in reasoning (41). That rests on 5 independent benchmark results, and every score on this page links to its publisher.
- How does JT-4.1 Flash 236B A21B rank?
- JT-4.1 Flash 236B A21B (no reasoning effort) is #331 of 785 ranked configurations on 25 Oct 2026. 389 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was JT-4.1 Flash 236B A21B released?
- China Mobile released JT-4.1 Flash 236B A21B on 9 Jul 2026. BenchLeader has results for it at 2 reasoning-effort settings.
Data as of 25 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “JT-4.1 Flash 236B A21B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/jt-4-1-flash-236b-a21b.