Qwen3.5-122B-A10B
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Updated 4 h ago · first seen 11 Sept 2026
model_01M294WW49F82VPVN986VP3Q7F
- Context
- 262.1K tokens
- T2 · 6 h ago
- Released
- 25 Feb 2026
- T2 · 6 h ago
Specification
- Release date
- 25 Feb 2026
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Openness
- open-weights
Source:Artificial AnalysisT2observed 4 h agomedium
- Context window
- 262.1K tokens
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Max output
- 65.5K tokens
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Modalities
- image, text, video
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Input modalities
- image, text, video
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Tokenizer
- Qwen3
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Hugging Face repo
- Qwen/Qwen3.5-122B-A10B
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Aa median output tokens per second
- 126.4
Source:Artificial AnalysisT2observed 4 h agomedium
- Openrouter id
- qwen/qwen3.5-122b-a10b
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
17
Source tiers
T217
Freshest observation
4 h ago
Conflicts
None
Modalities
- Modalities
- imagetextvideo
- Input
- imagetextvideo
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 262.1K tokens
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Max output
- 65.5K tokens
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
- Tokenizer
- Qwen3
Source:OpenRouter public model & pricing listingT2observed 6 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 93.57% | pass^1 | aa_slug=qwen3-5-122b-a10b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 16.19 | index | aa_slug=qwen3-5-122b-a10b · version=4.3 · estimated=false | — | artificialanalysis.aiT2 |
| GPQA | 85.66% | accuracy | aa_slug=qwen3-5-122b-a10b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 25.21% | accuracy | aa_slug=qwen3-5-122b-a10b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 75.71% | accuracy | aa_slug=qwen3-5-122b-a10b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| MMMU-Pro | 74.97% | accuracy | aa_slug=qwen3-5-122b-a10b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SciCode | 39.7% | accuracy | aa_slug=qwen3-5-122b-a10b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 0% | accuracy | aa_slug=qwen3-5-122b-a10b · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 47.57% | accuracy | aa_slug=qwen3-5-122b-a10b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 31.06% | accuracy | aa_slug=qwen3-5-122b-a10b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterqwen/qwen3.5-122b-a10b | $0.26 | $2.08 | — | — | 262.1K | 2 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
No hardware estimate available
Ancestors 0
None recorded.
This model
Qwen3.5-122B-A10B
Quantizations 2
Descendants 0
None recorded.
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Aa median output tokens per second
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 126.4 | → current | current | Artificial AnalysisT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Qwen3.5-122B-A10B scores 31.06% on Terminal-Bench
artificial_analysisQwen3.5-122B-A10B scores 47.57% on Terminal-Bench
artificial_analysisQwen3.5-122B-A10B scores 0% on Terminal-Bench
artificial_analysisQwen3.5-122B-A10B scores 93.57% on τ²-bench
artificial_analysisQwen3.5-122B-A10B scores 74.97% on MMMU-Pro
artificial_analysisQwen3.5-122B-A10B scores 75.71% on IFBench
artificial_analysisQwen3.5-122B-A10B scores 39.7% on SciCode
artificial_analysisQwen3.5-122B-A10B scores 25.21% on Humanity's Last Exam
artificial_analysisQwen3.5-122B-A10B scores 85.66% on GPQA
artificial_analysisQwen3.5-122B-A10B scores 16.19 on Artificial Analysis Intelligence Index
artificial_analysisOpenRouter lists Qwen3.5-122B-A10B at $0.26 in / $2.08 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/nvidia/Qwen3.5-122B-A10B-NVFP4 | model_page | T2· Quality secondary | 35 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/Intel/Qwen3.5-122B-A10B-int4-AutoRound | model_page | T2· Quality secondary | 45 min ago | 3 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 2 h ago | 4 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 4 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.