Qwen3.8 2.4T A95B
Qwen · released Aug 12, 2026
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
Specification
- Context window
- 1.05M
- Max output
- 131K
- Knowledge cutoff
- Not stated
- Parameters
- 2446.2B
- Licence
- other
- Serving providers
- 5
- Moderated
- No
- Uptime
- 100.0%
Intelligence
39.9
91th percentile
Coding
71.9
Coding Index
Agentic
50.1
Agentic Index
Output speed
114 t/s
Median across providers
Latency
799ms
Time to first token
Cost per task
$0.58
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond93.5%
- AA-LCR (long context)80.3%
- SciCode54.1%
- τ²-bench (Telecom)49.1%
- Humanity's Last Exam42.4%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 93.5% |
| AA-LCR (long context) | 80.3% |
| SciCode | 54.1% |
| τ²-bench (Telecom) | 49.1% |
| Humanity's Last Exam | 42.4% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Gemini 3.8 FlashGoogle40.9
- Claude Opus 4.7Anthropic40.7
- Qwen3.8 2.4T A95BQwen39.9
- Muse Spark 1.2Meta39.6
- V4.1 FlashDeepSeek39.5
- Gemini 3.7 FlashGoogle39.1
- GPT-5.4OpenAI39.0
- Grok 4.5xAI38.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Gemini 3.8 Flash | 40.9 |
| Claude Opus 4.7 | 40.7 |
| Qwen3.8 2.4T A95B | 39.9 |
| Muse Spark 1.2 | 39.6 |
| V4.1 Flash | 39.5 |
| Gemini 3.7 Flash | 39.1 |
| GPT-5.4 | 39.0 |
| Grok 4.5 | 38.8 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $2
- Output / 1M tokens
- $6
- Cached input / 1M
- $0.25
- Blended 3:1
- $3
One task, estimated
$0.58
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.