Skip to content
aiqbench

Alibaba · model passport

Qwen: Qwen3 8B

qwen3-8b
  • Open weights
  • 8.2B params
  • 131,072 context
  • Released 2025-04-29(curated)
7/27axes covered
Best percentile
92.4HHEM Hallucination (Vectara)
Cohort standing
51.4median 48.6

What the data says

Benchmarked on 7 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 92.4 pct — HHEM Hallucination (Vectara) (95.2%)

Uneven: 67.7 percentile points between its best and worst axis — 92.4 pct on HHEM Hallucination (Vectara) versus 24.7 pct on IFBench (Artificial Analysis).

  • HHEM Hallucination (Vectara)92.4 pct95.2%Verify →
  • BFCL v4 (function calling)Dormant board64.6 pct42.6%Verify →
  • LiveCodeBench (Artificial Analysis)50.4 pct40.6%Verify →
  • MMLU-Pro (Artificial Analysis)49.4 pct74.3%Verify →
  • AIME (math)41.5 pct56.1%Verify →
  • GPQA Diamond40.7 pct56.8%Verify →
  • IFBench (Artificial Analysis)24.7 pct33.5%Verify →
  • OverallNot benchmarked
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked
  • CodingNot benchmarked
  • Instruction followingNot benchmarked
  • Hard promptsNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

RepositoryQwen/Qwen3-8B
Parameters8.2B
ArchitectureQwen3ForCausalLM

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Qwen/Qwen3-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Use it hosted

API model IDqwen/qwen3-8b
Context length131,072 tokens
Max output8,192 tokens
Input price$0.12 per 1M tokens
Output price$0.46 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningMax tokensPresence penaltyReasoningResponse formatSeedStop sequencesTemperatureTool choiceTool callingTop-kTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3-8b","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • qwen3-8b stands at 51.4 (raw mean 52) — measured on 7 of 27 axes.

    standingtemplateVerify →

  • qwen3-8b stands at 51.4 versus a cohort median of 48.6 across 150 models released within 180 days — above the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →