Enter opens the highlighted result. Esc closes.

Qwen3.6 35B A3B vs Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B leads Qwen3.6 35B A3B on the Artificial Analysis Intelligence Index, 39.9 to 18.2, and Qwen3.6 35B A3B costs 6.0x less per output token ($1.00 vs $6.00 per million). Updated October 22, 2026; 7 benchmarks have a result for both.

Replace Qwen3.6 35B A3B Replace Qwen3.8 2.4T A95B
Qwen3.6 35B A3BQwen
Coding
No data
Overall
45.0
Output $/M
$1.00
0
Qwen3.8 2.4T A95BQwen
Coding
No data
Overall
No data
Output $/M
$6.00
7
vs boards won of 7 shared

Qwen3.6 35B A3B or Qwen3.8 2.4T A95B: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Qwen3.6 35B A3B for output tokens 6.0x cheaper ($1.00 vs $6.00 per million) and work measured by AA Coding Index or SciCode, where it leads.

Model AQwen3.6 35B A3BQwenNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.8 2.4T A95BQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
7
Qwen3.6 35B A3B only
13
Qwen3.8 2.4T A95B only
2
Like-for-like categories
5 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Qwen3.6 35B A3B not benchmarked, Qwen3.8 2.4T A95B not benchmarked.
Widest category
Agentic work, 37.0 points apart on average over 1 shared benchmark.
Widest single gap
AA Agentic Index: Qwen3.6 35B A3B 13.1 against Qwen3.8 2.4T A95B 50.1, 37.0 points apart on a 0 to 100 scale.
Output price
Qwen3.6 35B A3B $1.00 against Qwen3.8 2.4T A95B $6.00 per million output tokens, 6.0x apart.
Context window
Qwen3.6 35B A3B takes 262K tokens, Qwen3.8 2.4T A95B 1.05M.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryQwen3.6 35B A3BBarsQwen3.8 2.4T A95BTies
Coding02
Intelligence01
Agentic work01
Reasoning02
General01
All shared boards07
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
AA Coding Index41.971.9Qwen3.8 2.4T A95B
SciCode36.6%54.1%Qwen3.8 2.4T A95B
Terminal-Bench Hard (Artificial Analysis run)34.8%Not measuredOnly Qwen3.6 35B A3B measured
Terminal-Bench24.6%Not measuredOnly Qwen3.6 35B A3B measured
WeirdML34.5%Not measuredOnly Qwen3.6 35B A3B measured
Neither model has a result on the other 38 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
AA Intelligence Index18.239.9Qwen3.8 2.4T A95B
Epoch Capabilities Index143.7Not measuredOnly Qwen3.6 35B A3B measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
AA Agentic Index13.150.1Qwen3.8 2.4T A95B
τ²-Bench Telecom95.3%Not measuredOnly Qwen3.6 35B A3B measured
MCP AtlasNot measured84.5%Only Qwen3.8 2.4T A95B measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
Reasoning benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
GPQA Diamond (Artificial Analysis run)84.1%93.5%Qwen3.8 2.4T A95B
Humanity's Last Exam (Artificial Analysis run)22.2%42.4%Qwen3.8 2.4T A95B
GPQA Diamond (Epoch AI run)84.8%Not measuredOnly Qwen3.6 35B A3B measured
Mystery game puzzles22.0%Not measuredOnly Qwen3.6 35B A3B measured
Neither model has a result on the other 19 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Math benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
OTIS Mock AIME86.7%Not measuredOnly Qwen3.6 35B A3B measured
FrontierMath, tiers 1 to 320.4%Not measuredOnly Qwen3.6 35B A3B measured
MathArenaNot measured31.6%Only Qwen3.8 2.4T A95B measured
Neither model has a result on the other 11 boards here
KnowledgeNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Knowledge benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
Neither model has a result on 20 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
General benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
IFBench64.4%Not measuredOnly Qwen3.6 35B A3B measured
Long context reasoning (AA-LCR)71.7%80.3%Qwen3.8 2.4T A95B
DTBench73.9%Not measuredOnly Qwen3.6 35B A3B measured
LMCA29.7%Not measuredOnly Qwen3.6 35B A3B measured
Surface Evolver Bench44.4%Not measuredOnly Qwen3.6 35B A3B measured
Neither model has a result on the other 43 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
BenchmarkQwen3.6 35B A3BQwen3.8 2.4T A95BLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Qwen3.6 35B A3B$0.0006Fits in one request
Qwen3.8 2.4T A95B$0.0050Fits in one request

Qwen3.6 35B A3B costs less

Repository review

50K input + 3K output tokens

Qwen3.6 35B A3B$0.0080Fits in one request
Qwen3.8 2.4T A95B$0.118Fits in one request

Qwen3.6 35B A3B costs less

Agent loop

200K input + 10K output tokens

Qwen3.6 35B A3B$0.030Fits in one request
Qwen3.8 2.4T A95B$0.460Fits in one request

Qwen3.6 35B A3B costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Qwen3.6 35B A3B and Qwen3.8 2.4T A95B
SpecificationQwen3.6 35B A3BQwen3.8 2.4T A95B
MakerQwenQwen
WeightsOpen weightsOpen weights
ReleasedApril 27, 2026August 12, 2026
Context window262K1.05M
Input $/Mtok$0.10$2.00
Output $/Mtok$1.00$6.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen3.6 35B A3B better than Qwen3.8 2.4T A95B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Qwen3.6 35B A3B for output tokens 6.0x cheaper ($1.00 vs $6.00 per million) and work measured by AA Coding Index or SciCode, where it leads.

Which is cheaper, Qwen3.6 35B A3B or Qwen3.8 2.4T A95B?

Qwen3.6 35B A3B costs $0.10 per million input tokens and $1.00 per million output tokens; Qwen3.8 2.4T A95B costs $2.00 and $6.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen3.6 35B A3B or Qwen3.8 2.4T A95B?

Qwen3.8 2.4T A95B, with 1.05M tokens against 262K.

How many benchmarks is the Qwen3.6 35B A3B vs Qwen3.8 2.4T A95B comparison based on?

7 benchmarks have a result for both models as of October 22, 2026. Qwen3.6 35B A3B's coding index rests on 0 independent benchmarks and Qwen3.8 2.4T A95B's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next