Models / Qwen3-8B

Alibaba

Qwen3-8B

Qwen3-8B is best for sticking to the facts; it is not on sale through OpenRouter, so it is here for reference.

Results 16 Nov 2026 · 43 results · 4 sources

Price per million tokens
Not available through OpenRouter
Speed
Not measured
Intelligence Index
6.0
Artificial Analysis, at no reasoning; 5.2–6.0 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Alibaba, based in China
Weights not published
Released
28 Apr 2025 (Artificial Analysis)

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 174th of 186Claude Opus 5.5 – – –
Models from developers based in China 76th of 76MiMo-V2.6-Pro – – –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

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 127th of 160 available
BenchmarkQwen3-8BRank among availableBest available
Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported 42.6% 17th of 37 Claude Opus 4.5 77.5%
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 108 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 2.2% 104th of 108 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 4.7% 94th of 105 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: 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 162nd of 188 available
BenchmarkQwen3-8BRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 6.0 174th of 186 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 3.9% 172nd of 187 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 58.9% 134th of 169 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 150th of 170 available
BenchmarkQwen3-8BRank among availableBest available
UGI LeaderboardUGI: writing score · reported 28.0 108th 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 7th of 140 available
BenchmarkQwen3-8BRank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 4.8% 5th of 72 GPT-5.4 nano 3.1%
  • 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

Against Qwen3-8B, Intelligence Index 6.0. "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.

Qwen3-8BClaude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent from China
Claude Fable 5.2
leads overall
Qwen4-Max
Alibaba's best other model
Price per million tokens – $8.00$0.54$16.00$2.25
Tokens a second – 9643––
Intelligence Index 6.0 57.646.3––
Spring Prompt overall – 82–9056
Rank among available models, by use case
Product listings – 13th–5th19th
Decks from an analysis – 7th–4th1st
User surveys – 4th–1st5th
Marketing planning – 9th–1st15th
Agents and tool use 127th of 160 3rd22nd––
Professional work – 3rd–––
Reasoning and knowledge 162nd of 188 1st13th––
Writing 150th of 170 5th23rd––
Sticking to the facts 7th of 140 3rd9th––
Speed under pressure – ––8th26th

Shaded figures are better than Qwen3-8B'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 top quarter (by percentile) for sticking to the facts; in the bottom quarter for agents and tool use, reasoning and knowledge, and writing.

Artificial Analysis lists it but has not published a speed for it yet

Every result

43 published results from 4 sources, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 19 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 9.0 177 of 187 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 6.0 396 of 413 Qwen3-8B (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 5.2 407 of 413 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 45.2% 334 of 360 Qwen3-8B (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 58.9% 296 of 360 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 1.9% 417 of 419 Qwen3-8B (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 3.9% 388 of 419 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 28.6% 275 of 288 Qwen3-8B (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 33.5% 245 of 288 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 0.0% 390 of 407 Qwen3-8B (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 0.0% 390 of 407 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 27.9% 196 of 205 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 2.2% 178 of 188 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 2.3% 260 of 282 Qwen3-8B (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 2.3% 260 of 282 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 4.7% 161 of 175 Qwen3-8B (thinking reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 24.9% 236 of 286 Qwen3-8B (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 27.8% 223 of 286 Qwen3-8B (thinking reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 16 results
MeasureValueRankConfigurationDated
BFCL: irrelevance detection% correct, higher is better 79.1% 64 of 109 Qwen3-8B (bfcl fc) 16 Dec 2025
BFCL: irrelevance detection% correct, higher is better 82.3% 46 of 109 Qwen3-8B (bfcl prompt) 16 Dec 2025
BFCL: memory% correct, higher is better 14.6% 57 of 109 Qwen3-8B (bfcl fc) 16 Dec 2025
BFCL: memory% correct, higher is better 13.1% 63 of 109 Qwen3-8B (bfcl prompt) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 41.8% 26 of 109 Qwen3-8B (bfcl fc) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 33.4% 39 of 109 Qwen3-8B (bfcl prompt) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 42.6% 39 of 109 Qwen3-8B (bfcl fc) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 40.4% 44 of 109 Qwen3-8B (bfcl prompt) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 93.8% 8 of 109 Qwen3-8B (bfcl fc) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 75.0% 62 of 109 Qwen3-8B (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 87.6% 24 of 109 Qwen3-8B (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 88.6% 16 of 109 Qwen3-8B (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 80.5% 11 of 109 Qwen3-8B (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 80.1% 12 of 109 Qwen3-8B (bfcl prompt) 16 Dec 2025
BFCL: web search% correct, higher is better 12.0% 53 of 109 Qwen3-8B (bfcl fc) 16 Dec 2025
BFCL: web search% correct, higher is better 13.5% 50 of 109 Qwen3-8B (bfcl prompt) 16 Dec 2025

Not shown: Not general refusal or safety behaviour.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 17.0% 148 of 379 Qwen3-8B (no reasoning) 12 Sep 2025
UGI: requested-length error% off the requested word count, lower is better 64.0% 335 of 379 Qwen3-8B (thinking reasoning) 9 Nov 2025
UGI: style adherencescore from 0 to 1, higher is better 0.36 126 of 379 Qwen3-8B (no reasoning) 12 Sep 2025
UGI: style adherencescore from 0 to 1, higher is better 0.35 193 of 379 Qwen3-8B (thinking reasoning) 9 Nov 2025
UGI: writing scorescore out of 100, higher is better 28.0 293 of 379 Qwen3-8B (no reasoning) 12 Sep 2025
UGI: writing scorescore out of 100, higher is better 23.9 322 of 379 Qwen3-8B (thinking reasoning) 9 Nov 2025

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

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 99.9% 19 of 108 Qwen3-8B 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 4.8% 9 of 108 Qwen3-8B 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Test your own prompt.

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