AlibabaQwen3 8B
Qwen3 8B is an Alibaba open-weights model, released 28 Apr 2025. Its best configuration (thinking reasoning effort) ranks #708 of 785 on the BenchLeader Index at 38.6 ±3.7, in the lower half. The ± is the point: 216 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 reasoning (41) and lowest in long context (23). At $0.310 per million tokens blended it is cheaper than most ranked models. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 28 Apr 2025.stale: no new result in six months
- Blended price
- $0.310/M
- $0.180 in · $0.700 out
- Output speed
- –
- First answer
- –
- Context
- 131k
- Full answer
- –
- Cost per run
- –
- Released
- 28 Apr 2025
- Overall index39
- Reasoning41
- Agents & tools33
- Knowledge32
- Instruction following37
- Long context23
- Composite35
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 reasoning | 37.3 | #736 | – | – | $0.0001 | Agents & tools 36 · Composite 36 · Instruction following 33 · Knowledge 28 · Long context 23 · Maths 33 · Reasoning 39 |
| thinkingbest | 38.6 | #708 | – | – | $0.0003 | Agents & tools 33 · Composite 35 · Instruction following 37 · Knowledge 32 · Long context 23 · Reasoning 41 |
| not stated | – | – | – | – | $0.0003 | Agents & tools 54 · Coding 16 · Maths 48 · Reasoning 43 |
How its index has moved
9 Sept 2026 to 21 Oct 2026- thinking
- no reasoning
The 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 | not stated | Source | Trend |
|---|---|---|---|---|---|
| GPQA Diamond | 47.5%#225 | – | 56.8%#198 | Epoch AI Benchmarking Hub | |
| GPQA Diamond (AA)not in index | 45.1%#452 | 58.9%#382 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 1.9%#614 | 3.9%#557 | – | Artificial Analysis | |
| CritPt | 0.0%#315 | 0.0%#315 | – | Artificial Analysis | |
| LMCAnot in indexeffort not stated | – | – | 8.8%#183 | Epoch AI Benchmarking Hub | |
| DTBenchnot in indexeffort not stated | – | – | 59.7%#188 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | thinking | not stated | Source | Trend |
|---|---|---|---|---|
| SciCodeeffort not stated | – | 22.6%#211 | SciCode | |
| SciCode (AA)not in index | 27.9%#214 | – | Artificial Analysis | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | – | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 2.3%#220 | – | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| Terminal-Bench Hard | 2.3%#320 | 2.3%#320 | – | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 24.9%#296 | 27.8%#272 | – | Artificial Analysis | |
| BFCL Overalleffort not stated | – | – | 42.6%#31 | Berkeley Function Calling Leaderboard | |
| τ³-Banking (AA) | – | 4.7%#188 | – | Artificial Analysis | |
| AutomationBenchnot in index | – | 0.3%#212 | – | Artificial Analysis | |
| GDP.pdf (AA)not in index | – | 1.4%#196 | – | Artificial Analysis |
Maths
| Benchmark | no reasoning | not stated | Source | Trend |
|---|---|---|---|---|
| OTIS Mock AIME | 22.2%#220 | 56.1%#172 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| AA-Omniscience | -74.0#526 | -64.7#496 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 11.1%#485 | 13.6%#453 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 4.4%#532 | 9.3%#431 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| IFBench | 28.6%#372 | 33.5%#327 | Artificial Analysis |
Long context
| Benchmark | no reasoning | thinking | Source | Trend |
|---|---|---|---|---|
| AA-LCR | 0.0%#493 | 0.0%#493 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | 136.1#129 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 6.0#547 | 5.2#601 | – | Artificial Analysis |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| PropensityBenchnot in index | 75.2%#3 | Scale AI SEAL |
Price history
The price above, per 1M tokens, every day it changed.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.039 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0003 | $0.0002 | – |
| Summarize a 30-page report | 12,000 / 600 | $0.0026 | $0.0013 | – |
| Code edit | 6,000 / 1,500 | $0.0021 | $0.0015 | – |
| Agentic coding session | 60,000 / 4,000 | $0.014 | $0.0073 | – |
| Structured extraction | 2,000 / 200 | $0.0005 | $0.0003 | – |
See also
Questions people ask
- What are Qwen3 8B's benchmark scores?
- As of 24 Oct 2026, Qwen3 8B (thinking effort) scores 38.6 ±3.7 on the BenchLeader Index, strongest in reasoning (41) and weakest in long context (23). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
- How does Qwen3 8B rank?
- Qwen3 8B (thinking effort) is #708 of 785 ranked configurations on 24 Oct 2026. 216 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.
- How much does Qwen3 8B cost per 1M tokens?
- As of 24 Oct 2026, Qwen3 8B costs $0.180 per 1M input tokens and $0.700 per 1M output tokens, $0.310 blended (three input tokens per output token). The list price last changed on 24 Oct 2026.
- When was Qwen3 8B released?
- Alibaba released Qwen3 8B on 28 Apr 2025. BenchLeader has results for it at 3 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Qwen3 8B: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/qwen3-8b.