Data as of November 11, 2026 · How the score is built
Released Mar 4, 2026262K context
Qwen3.5-122B-A10B
Decision readingQwen3.5-122B-A10B scores 52.6 out of 100 and ranks #91 of 214. This profile shows 20 source-displayable benchmark rows; its strongest eligible category is Multilingual at #9. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.
Released Mar 4, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
52.6/100
field median 51.2#91 of 214 ranked models
Public
#91of 214
Verified —
Price
Self-hosted; infrastructure cost varies
input median $0.60No comparable first-party hosted token rate
Speed
134tok/s
field median 92 tok/sFirst token 17.24 s
Context
262Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Multilingual ranks #9. A well-rounded choice across a range of tasks.
Validate before choosing
20 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 20 displayable benchmark rows
Is Qwen3.5-122B-A10B right for your job?
Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.
Where Qwen3.5-122B-A10B ranks by benchmark score:
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #95 of 132Percentile 28thWeight 22%3 benchmarksVerified | 33.4 | 3 benchmarks | Verified | |||
| CodingRank #87 of 158Percentile 45thWeight 20%3 benchmarksVerified | 35.4 | 3 benchmarks | Verified | |||
| ReasoningRank #81 of 158Percentile 49thWeight 17%1 benchmarkVerified | 40.2 | 1 benchmark | Verified | |||
| MultimodalRank #52 of 67Percentile 23rdWeight 12%6 benchmarksMixed sources | 51.4 | 6 benchmarks | Mixed sources | |||
| KnowledgeRank #89 of 179Percentile 51stWeight 12%3 benchmarksVerified | 48.0 | 3 benchmarks | Verified | |||
| MultilingualRank #9 of 17Percentile 50thWeight 7%1 benchmarkVerified | 87.1 | 1 benchmark | Verified | |||
| Inst. FollowingRank #13 of 157Percentile 92ndWeight 5%1 benchmarkVerified | 93.0 | 1 benchmark | Verified | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
20 of 894 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic3/3 verified
- Coding3/3 verified
- Reasoning1/1 verified
- Multimodal4/6 verified
- Knowledge3/3 verified
- Multilingual1/1 verified
- Inst. Following1/1 verified
- MathNot measured
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Qwen3.5-122B-A10B category percentile values
- Agentic28th percentile
- Coding45th percentile
- Reasoning49th percentile
- Multimodal23rd percentile
- Knowledge51st percentile
- Multilingual50th percentile
- Instruction following92nd percentile
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#95/132
- Coding#87/158
- Reasoning#81/158
- Multimodal#52/67
- Knowledge#89/179
- Multilingual#9/17
- Inst. Following#13/157
- MathNot ranked
Benchmark ledger
Every result says who ran the test. For this model, Alibaba ran 16 of 20. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.
Coding3 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | 49.4% | Best verified: GPT-5.5 · 82.0% | Gap32.6 behind | Reported by Alibaba | CountsScored in Agentic |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | 72% | Best verified: Claude Opus 5 · 96% | Gap24 behind | Reported by Alibaba | Shown only |
| LiveCodeBench v6 | 78.9% | Best verified: Sakana Fugu-Ultra · 93.2% | Gap14.3 behind | Reported by Alibaba | Shown only |
Agentic3 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| BrowseComp | 63.8% | Best verified: Atria Dawn Preview · 92.5% | Gap28.7 behind | Reported by Alibaba | Counts8% ref. weight |
| Terminal-Bench 2.0 | 49.4% | Best verified: GPT-5.5 · 82% | Gap32.6 behind | Reported by Alibaba | Counts7% ref. weight |
| OSWorld-Verified | 58% | Best verified: Qwen3.8 Max · 86.1% | Gap28.1 behind | Reported by Alibaba | Counts7% ref. weight |
Reasoning1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| LongBench v2 | 60.2% | Best verified: Inkling 2 Small · 70.6% | Gap10.4 behind | Reported by Alibaba | Counts5% ref. weight |
Multimodal6 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | 76.9% | Best verified: GPT-6.1 Terra · 85.5% | Gap8.6 behind | Reported by Alibaba | Counts30% ref. weight |
| CharXivCharXiv Reasoning | 77.2% | Best verified: Qwen3.8 Max · 93.5% | Gap16.3 behind | Reported by Alibaba | Counts17% ref. weight |
| MMMUMassive Multi-discipline Multimodal Understanding | 83.9% | Best verified: Qwen3.5 397B · 85.0% | Gap1.1 behind | Carried from an upstream page | Shown only |
| MMVUMultimodal Multi-disciplinary Video Understanding | 74.7% | Best verified: Qwen3.8 Max · 82.4% | Gap7.7 behind | Carried from an upstream page | Shown only |
| MathVision | 86.2% | Best verified: Qwen3.8 Max · 95.2% | Gap9 behind | Reported by Alibaba | Shown only |
| V* | 93.2% | Best verified: Kimi K2.6 · 96.9% | Gap3.7 behind | Reported by Alibaba | Shown only |
Knowledge3 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMLU-ProMassive Multitask Language Understanding Professional | 86.7% | Best verified: Qwen3.7 Max · 89.6% | Gap2.9 behind | Reported by Alibaba | Counts6% ref. weight |
| GPQAGraduate-Level Google-Proof Q&A | 86.6% | Best verified: GPT-6 Astra · 96% | Gap9.4 behind | Reported by Alibaba | Counts3% ref. weight |
| SuperGPQASuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | 67.1% | Best verified: Qwen 3.6 Max (preview) · 73.9% | Gap6.8 behind | Reported by Alibaba | Counts2% ref. weight |
Multilingual1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMLU-ProX | 82.2% | Best verified: Qwen3.7 Max · 87% | Gap4.8 behind | Reported by Alibaba | CountsWeighted 100% |
Inst. Following1 row
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| IFEvalInstruction-Following Eval | 93.4% | Best verified: LFM2.5-24B-A2B · 96.8% | Gap3.3 behind | Reported by Alibaba | Shown only |
External signals2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| NYT ConnectionsNYT Connections LLM Benchmark (extended version) | 51.7% | Best verified: Gemini 4 Argon · 98.6% | Gap46.9 behind | Run by NYT Connections | Shown only |
| Mystery Game PuzzlesMystery Game Puzzles (Epoch AI) | 17.0% | Best verified: Claude Fable 5.2 · 90.0% | Gap73 behind | Run by Mystery Game Puzzles | Shown only |
Outlined bars are lab-reported or carried from an upstream page. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 262K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, image, videoQwen3.5-122B-A10B model card
- Output modalities
- textQwen3.5-122B-A10B model card
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Qwen3.5-122B-A10B needs ~80GB VRAM (1× NVIDIA H100 (80GB)).
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Qwen3.5-122B-A10B ranks #91 of 214 on the public leaderboard with a score of 52.64/100. It does not yet have enough sourced coverage for a verified position.
Qwen3.5-122B-A10B is a open weight model with a 262K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Official exact-value benchmark snapshot from the Qwen/Qwen3.5-122B-A10B-FP8 model card. Native context is 262,144 tokens and the model card notes extensibility up to roughly 1M tokens with RoPE scaling.
20 of 894 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multilingual at #9, while its lowest eligible position is Agentic at #95. a well-rounded choice across a range of tasks.
Last updated November 11, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run Qwen3.5-122B-A10B by API
2 hosts publish a per-token price for it. OpenRouter has the lowest output rate, $2.08 per million tokens. Prices read from each host’s own pages on November 11, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context |
|---|---|---|---|---|
| OpenRouter | $0.26 | $2.08 | — | 262K |
| Novita AI | $0.40 | $3.20 | — | 262K |
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Questions
How does Qwen3.5-122B-A10B perform overall in AI benchmarks?
Qwen3.5-122B-A10B ranks #91 out of 214 models on the public BenchAlign leaderboard, with a score of 52.64/100. Its evidence status is Estimated, and this profile shows 20 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Qwen3.5-122B-A10B good for knowledge and understanding?
Qwen3.5-122B-A10B ranks #89 out of 179 eligible models for knowledge and understanding, with a public category score of 48/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.5-122B-A10B good for coding and programming?
Qwen3.5-122B-A10B ranks #87 out of 158 eligible models for coding and programming, with a public category score of 35.4/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.5-122B-A10B good for reasoning and logic?
Qwen3.5-122B-A10B ranks #81 out of 158 eligible models for reasoning and logic, with a public category score of 40.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.5-122B-A10B good for agentic tool use and computer tasks?
Qwen3.5-122B-A10B ranks #95 out of 132 eligible models for agentic tool use and computer tasks, with a public category score of 33.4/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.5-122B-A10B good for multimodal and grounded tasks?
Qwen3.5-122B-A10B ranks #52 out of 67 eligible models for multimodal and grounded tasks, with a public category score of 51.4/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.5-122B-A10B good for instruction following?
Qwen3.5-122B-A10B ranks #13 out of 157 eligible models for instruction following, with a public category score of 93/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.5-122B-A10B good for multilingual tasks?
Qwen3.5-122B-A10B ranks #9 out of 17 eligible models for multilingual tasks, with a public category score of 87.1/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Qwen3.5-122B-A10B open source?
Qwen3.5-122B-A10B is an open-weight model from Alibaba. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Qwen3.5-122B-A10B have full benchmark coverage on BenchLM?
No. Qwen3.5-122B-A10B currently has 33 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has a reported context window of 262K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.