Models / Nanbeige4-3B-Thinking (2511)

Nanbeige

Nanbeige4-3B-Thinking (2511)

Early evidence, 11 results from 2 sources, on 2 use cases. Nanbeige4-3B-Thinking (2511) is strongest at agents and tool use; it is not on sale through OpenRouter, so it is here for reference.

Results 16 Nov 2026 · 11 results · 2 sources

Price per million tokens
Not available through OpenRouter
Speed
Not measured
Intelligence Index
Not measured
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Nanbeige
Weights not published
Released
Not recorded
no launch date in our tracker or our sources

How good is it, and for what?

Each use case ranks the available models its benchmarks measured. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 59th of 160 available
BenchmarkNanbeige4-3B-Thinking (2511)Rank among availableBest available
Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported 51.4% 14th of 37 Claude Opus 4.5 77.5%
  • tau2-bench: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge Not measured
  • Artificial Analysis: has not measured this model.
WritingWhat people prefer in blind comparisons, and judged writing quality 170th of 170 available
BenchmarkNanbeige4-3B-Thinking (2511)Rank among availableBest available
UGI LeaderboardUGI: writing score · reported 9.8 125th of 125 Gemini 3.8 Flash 78.6
  • Arena (formerly LMArena): has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers Not measured
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

  • The most capable open-weights modelMiMo-V2.6-Pro$0.54 blended · Intelligence Index 46.3

Against Nanbeige4-3B-Thinking (2511). "Similar intelligence" means within 4 points or better.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Nanbeige4-3B-Thinking (2511)Claude Fable 5.2
leads overall
Claude Opus 5.5
near the top overall
GPT-6.1 Sol
near the top overall
GPT-6.1 Terra
near the top overall
Price per million tokens – $16.00$8.00$4.00$2.00
Tokens a second – –9653–
Intelligence Index – –57.651.8–
Spring Prompt overall – 90828080
Rank among available models, by use case
Product listings – 5th13th2nd4th
Decks from an analysis – 4th7th5th8th
User surveys – 1st4th3rd8th
Marketing planning – 1st9th–2nd
Agents and tool use 59th of 160 –3rd6th7th
Professional work – –3rd9th–
Reasoning and knowledge – –1st6th22nd
Writing 170th of 170 –5th16th–
Sticking to the facts – –3rd18th–
Speed under pressure – 8th–3rd17th

Shaded figures are better than Nanbeige4-3B-Thinking (2511)'s. A dash means no result.

Where it has been measured

Compared with the models available today (it is not on sale itself), in the bottom quarter for writing.

Not timed: Artificial Analysis, our source for speed, has not tested it

Every result

11 published results from 2 sources, each in the source's own units, with the configuration that produced it.

Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 8 results
MeasureValueRankConfigurationDated
BFCL: irrelevance detection% correct, higher is better 83.1% 42 of 109 Nanbeige4-3B-Thinking (2511, bfcl fc) 16 Dec 2025
BFCL: memory% correct, higher is better 36.8% 19 of 109 Nanbeige4-3B-Thinking (2511, bfcl fc) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 51.1% 15 of 109 Nanbeige4-3B-Thinking (2511, bfcl fc) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 51.4% 25 of 109 Nanbeige4-3B-Thinking (2511, bfcl fc) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 75.0% 62 of 109 Nanbeige4-3B-Thinking (2511, bfcl fc) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 81.6% 71 of 109 Nanbeige4-3B-Thinking (2511, bfcl fc) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 79.4% 15 of 109 Nanbeige4-3B-Thinking (2511, bfcl fc) 16 Dec 2025
BFCL: web search% correct, higher is better 21.5% 41 of 109 Nanbeige4-3B-Thinking (2511, bfcl fc) 16 Dec 2025

Not shown: Not general refusal or safety behaviour.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 173.0% 374 of 379 Nanbeige4-3B-Thinking (2511) 18 Jan 2026
UGI: style adherencescore from 0 to 1, higher is better 0.26 377 of 379 Nanbeige4-3B-Thinking (2511) 18 Jan 2026
UGI: writing scorescore out of 100, higher is better 9.8 374 of 379 Nanbeige4-3B-Thinking (2511) 18 Jan 2026

Not shown: Not other format limits such as character counts or bullet counts.

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.