Reasoning
Like-for-like- Qwen3.5-122B-A10B
- 60.2
- Qwen3.6 Plus
- 62.0
- Weighted basis
- 1 vs 1 rows
- Reading
- Qwen3.6 Plus leads
Qwen3.5-122B-A10B vs Qwen3.6 Plus
Updated August 18, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Qwen3.6 Plus has the higher public score estimate, 64.79 versus 59.64, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
12 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Long documents
Prompts that approach the documented context limit
Qwen3.6 Plus
Qwen3.6 Plus has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
3 Qwen3.5-122B-A10B only
12 Shared
32 Qwen3.6 Plus only
- Shared results
- 12
- Qwen3.5-122B-A10B only
- 3
- Qwen3.6 Plus only
- 32
- Like-for-like categories
- 2 / 8
5 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Multilingual
Like-for-like- Qwen3.5-122B-A10B
- 82.2
- Qwen3.6 Plus
- 84.7
- Weighted basis
- 1 vs 1 rows
- Reading
- Qwen3.6 Plus leads
Agentic
Directional only- Qwen3.5-122B-A10B
- 56.4
- Qwen3.6 Plus
- 61.6
- Weighted basis
- 3 vs 1 rows
- Reading
- Directional only
Coding
Directional only- Qwen3.5-122B-A10B
- 72.0
- Qwen3.6 Plus
- 70.3
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Knowledge
Directional only- Qwen3.5-122B-A10B
- 83.6
- Qwen3.6 Plus
- 57.1
- Weighted basis
- 3 vs 4 rows
- Reading
- Directional only
Multimodal
Directional only- Qwen3.5-122B-A10B
- 77.2
- Qwen3.6 Plus
- 79.8
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Instruction following
Directional only- Qwen3.5-122B-A10B
- 93.4
- Qwen3.6 Plus
- 82.3
- Weighted basis
- 1 vs 2 rows
- Reading
- Directional only
Math
Not comparable- Qwen3.5-122B-A10B
- Not measured
- Qwen3.6 Plus
- 60.5
- Weighted basis
- 0 vs 4 rows
- Reading
- Not comparable
| Category | Qwen3.5-122B-A10B | Qwen3.6 Plus | Weighted basis | Reading |
|---|---|---|---|---|
| Reasoning | 60.2 | 62.0 | Like-for-like1 vs 1 rows | Qwen3.6 Plus leads |
| Multilingual | 82.2 | 84.7 | Like-for-like1 vs 1 rows | Qwen3.6 Plus leads |
| Agentic | 56.4 | 61.6 | Directional only3 vs 1 rows | Directional only |
| Coding | 72.0 | 70.3 | Directional only1 vs 2 rows | Directional only |
| Knowledge | 83.6 | 57.1 | Directional only3 vs 4 rows | Directional only |
| Multimodal | 77.2 | 79.8 | Directional only1 vs 2 rows | Directional only |
| Instruction following | 93.4 | 82.3 | Directional only1 vs 2 rows | Directional only |
| Math | Not measured | 60.5 | Not comparable0 vs 4 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
Terminal-Bench 2.0
Agentic
Qwen3.5-122B-A10B: 49.4%Qwen3.6 Plus: 61.6%Normalized gap 12.2Qwen3.5-122B-A10B source Qwen3.6 Plus sourceSWE-bench Verified
Coding
Qwen3.5-122B-A10B: 72%Qwen3.6 Plus: 78.8%Normalized gap 6.8Qwen3.5-122B-A10B source Qwen3.6 Plus sourceSuperGPQA
Knowledge
Qwen3.5-122B-A10B: 67.1%Qwen3.6 Plus: 71.6%Normalized gap 4.5Qwen3.5-122B-A10B source Qwen3.6 Plus sourceCharXiv
Multimodal
Qwen3.5-122B-A10B: 77.2%Qwen3.6 Plus: 81.5%Normalized gap 4.3Qwen3.5-122B-A10B source Qwen3.6 Plus sourceGPQA
Knowledge
Qwen3.5-122B-A10B: 86.6%Qwen3.6 Plus: 90.4%Normalized gap 3.8Qwen3.5-122B-A10B source Qwen3.6 Plus source
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Qwen3.6 Plus
- API rate not published
- Fits in one request
Qwen3.5-122B-A10B has no comparable published API token rate. Qwen3.6 Plus has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Qwen3.6 Plus
- API rate not published
- Fits in one request
Qwen3.5-122B-A10B has no comparable published API token rate. Qwen3.6 Plus has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Qwen3.5-122B-A10B
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
- Qwen3.6 Plus
- API rate not published
- Fits in one request
- Cached-input rate unavailable
Qwen3.5-122B-A10B has no comparable published API token rate. Qwen3.6 Plus has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationQwen3.5-122B-A10BQwen3.6 Plus
Context window
Maximum documented context; output-token limits may be lower.
Qwen3.5-122B-A10B
262K
Qwen3.6 Plus
1M
API model ID
Qwen3.5-122B-A10B
Not sourced
Qwen3.6 Plus
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Qwen3.5-122B-A10B
No comparable hosted API rate
Qwen3.6 Plus
No comparable hosted API rate
Documented inputs
Qwen3.5-122B-A10B
Not sourced
Qwen3.6 Plus
Not sourced
Documented outputs
Qwen3.5-122B-A10B
Not sourced
Qwen3.6 Plus
Not sourced
Provider availability
Qwen3.5-122B-A10B
Not sourced
Qwen3.6 Plus
Not sourced
Reasoning profile
Qwen3.5-122B-A10B
Reasoning
Qwen3.6 Plus
Reasoning
Weight access
Qwen3.5-122B-A10B
Open Weight
Qwen3.6 Plus
Proprietary
License
Qwen3.5-122B-A10B
Open Weight
Qwen3.6 Plus
Proprietary
Release date
Qwen3.5-122B-A10B
2026-03-04
Qwen3.6 Plus
2026-04-02
If you already use one of these models
- Deployment change
- Both entries list Alibaba as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Qwen3.6 Plus has the higher public score estimate, 64.79 versus 59.64, but the 90% score intervals overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Qwen3.6 Plus has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence47 rows
Agentic
Terminal-Bench 2.0
Qwen3.5-122B-A10B49.4%SourceQwen3.6 Plus61.6%SourceQwen3.6 Plus leads this result
BrowseComp
Qwen3.5-122B-A10B63.8%SourceQwen3.6 Plus—Not directly comparable
OSWorld-Verified
Qwen3.5-122B-A10B58%SourceQwen3.6 Plus—Not directly comparable
Claw-Eval
Qwen3.5-122B-A10B—Qwen3.6 Plus58.8%SourceNot directly comparable
QwenClawBench
Qwen3.5-122B-A10B—Qwen3.6 Plus57.2%SourceNot directly comparable
τ³-bench results
Qwen3.5-122B-A10B—Qwen3.6 Plus70.7%SourceNot directly comparable
VITA-Bench
Qwen3.5-122B-A10B—Qwen3.6 Plus44.3%SourceNot directly comparable
DeepPlanning
Qwen3.5-122B-A10B—Qwen3.6 Plus41.5%SourceNot directly comparable
Toolathlon
Qwen3.5-122B-A10B—Qwen3.6 Plus39.8%SourceNot directly comparable
MCP Atlas
Qwen3.5-122B-A10B—Qwen3.6 Plus48.2%SourceNot directly comparable
MCP-Tasks
Qwen3.5-122B-A10B—Qwen3.6 Plus74.1%SourceNot directly comparable
WideResearch
Qwen3.5-122B-A10B—Qwen3.6 Plus74.3%SourceNot directly comparable
Gert Labs
Qwen3.5-122B-A10B—Qwen3.6 Plus50.60%SourceNot directly comparable
ResearchClawBench
Qwen3.5-122B-A10B—Qwen3.6 Plus18.0%SourceNot directly comparable
Coding
SWE-bench Verified
Qwen3.5-122B-A10B72%SourceQwen3.6 Plus78.8%SourceQwen3.6 Plus leads this result
SWE-bench Pro
Qwen3.5-122B-A10B—Qwen3.6 Plus56.6%SourceNot directly comparable
SWE Multilingual
Qwen3.5-122B-A10B—Qwen3.6 Plus73.8%SourceNot directly comparable
LiveCodeBench v6
Qwen3.5-122B-A10B—Qwen3.6 Plus87.1%SourceNot directly comparable
Vibe Code Bench
Qwen3.5-122B-A10B—Qwen3.6 Plus25.56%SourceNot directly comparable
EEBench
Qwen3.5-122B-A10B—Qwen3.6 Plus12.7%SourceNot directly comparable
Reasoning
Knowledge
MMLU-Pro
Qwen3.5-122B-A10B86.7%SourceQwen3.6 Plus88.5%SourceQwen3.6 Plus leads this result
SuperGPQA
Qwen3.5-122B-A10B67.1%SourceQwen3.6 Plus71.6%SourceQwen3.6 Plus leads this result
GPQA
Qwen3.5-122B-A10B86.6%SourceQwen3.6 Plus90.4%SourceQwen3.6 Plus leads this result
MMLU-Redux
Qwen3.5-122B-A10B—Qwen3.6 Plus94.5%SourceNot directly comparable
C-Eval
Qwen3.5-122B-A10B—Qwen3.6 Plus93.3%SourceNot directly comparable
HLE
Qwen3.5-122B-A10B—Qwen3.6 Plus28.8%SourceNot directly comparable
Math
AIME26
Qwen3.5-122B-A10B—Qwen3.6 Plus95.3%SourceNot directly comparable
HMMT Feb 2025
Qwen3.5-122B-A10B—Qwen3.6 Plus96.7%SourceNot directly comparable
HMMT Nov 2025
Qwen3.5-122B-A10B—Qwen3.6 Plus94.6%SourceNot directly comparable
HMMT Feb 2026
Qwen3.5-122B-A10B—Qwen3.6 Plus87.8%SourceNot directly comparable
MMAnswerBench
Qwen3.5-122B-A10B—Qwen3.6 Plus83.8%SourceNot directly comparable
FrontierMath v2 (Tiers 1-3)
Qwen3.5-122B-A10B—Qwen3.6 Plus26.207%SourceNot directly comparable
FrontierMath v2 (Tier 4)
Qwen3.5-122B-A10B—Qwen3.6 Plus8.333%SourceNot directly comparable
Multilingual
Multimodal
MMMU
Qwen3.5-122B-A10B83.9%SourceQwen3.6 Plus86.0%SourceQwen3.6 Plus leads this result
MMVU
Qwen3.5-122B-A10B74.7%SourceQwen3.6 Plus—Not directly comparable
MathVision
Qwen3.5-122B-A10B86.2%SourceQwen3.6 Plus88.0%SourceQwen3.6 Plus leads this result
CharXiv
Qwen3.5-122B-A10B77.2%SourceQwen3.6 Plus81.5%SourceQwen3.6 Plus leads this result
V*
Qwen3.5-122B-A10B93.2%SourceQwen3.6 Plus96.9%SourceQwen3.6 Plus leads this result
MMMU-Pro
Qwen3.5-122B-A10B—Qwen3.6 Plus78.8%SourceNot directly comparable
VideoMMMU
Qwen3.5-122B-A10B—Qwen3.6 Plus84.0%SourceNot directly comparable
ScreenSpot Pro
Qwen3.5-122B-A10B—Qwen3.6 Plus68.2%SourceNot directly comparable
Instruction following
Frequently asked questions
Which is better, Qwen3.5-122B-A10B or Qwen3.6 Plus?
Qwen3.6 Plus has the higher public score estimate, 64.79 versus 59.64, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Qwen3.5-122B-A10B or Qwen3.6 Plus?
The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Qwen3.5-122B-A10B or Qwen3.6 Plus?
The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Qwen3.5-122B-A10B or Qwen3.6 Plus?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Qwen3.5-122B-A10B or Qwen3.6 Plus?
Qwen3.6 Plus has the larger documented context window: 1M, compared with 262K.
Related comparisons
Last updated August 18, 2026
Watch Qwen3.5-122B-A10B vs Qwen3.6 Plus
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.