Enter opens the highlighted result. Esc closes.

GPT-4 Turbo vs Qwen3.5-122B-A10B

Qwen3.5-122B-A10B leads GPT-4 Turbo on the Artificial Analysis Intelligence Index, 17.7 to 7.0, and Qwen3.5-122B-A10B costs 14.4x less per output token ($2.08 vs $30.00 per million). Updated October 23, 2026; 36 benchmarks have a result for both.

Replace GPT-4 Turbo Replace Qwen3.5-122B-A10B
GPT-4 TurboOpenAI
Coding
No data
Overall
No data
Output $/M
$30.00
0
Qwen3.5-122B-A10BQwen
Coding
No data
Overall
No data
Output $/M
$2.08
36
vs boards won of 36 shared

GPT-4 Turbo or Qwen3.5-122B-A10B: which to pick

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

Pick GPT-4 Turbo for work measured by AA Coding Index or LMArena Text: coding, where it leads.

Model AGPT-4 TurboOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.5-122B-A10BQwenNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
36
GPT-4 Turbo only
6
Qwen3.5-122B-A10B only
15
Like-for-like categories
6 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
GPT-4 Turbo not benchmarked, Qwen3.5-122B-A10B not benchmarked.
Widest category
Knowledge, 29.6 points apart on average over 4 shared benchmarks.
Widest single gap
LMArena Vision: Chinese: GPT-4 Turbo 1045 against Qwen3.5-122B-A10B 1301, 42.6 points apart on a 0 to 100 scale.
Output price
GPT-4 Turbo $30.00 against Qwen3.5-122B-A10B $2.08 per million output tokens, 14.4x apart.
Context window
GPT-4 Turbo takes 128K tokens, Qwen3.5-122B-A10B 262K.

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
CategoryGPT-4 TurboBarsQwen3.5-122B-A10BTies
Coding03
Intelligence01
Reasoning04
Math02
Knowledge04
General022
All shared boards036
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
LMArena WebDevNot measured1361Only Qwen3.5-122B-A10B measured
AA Coding Index21.543.3Qwen3.5-122B-A10B
LiveCodeBench (Artificial Analysis run)29.1%Not measuredOnly GPT-4 Turbo measured
SciCodeNot measured39.7%Only Qwen3.5-122B-A10B measured
Terminal-Bench Hard (Artificial Analysis run)Not measured31.1%Only Qwen3.5-122B-A10B measured
LMArena Text: coding12681436Qwen3.5-122B-A10B
LMArena Text: software and IT12671436Qwen3.5-122B-A10B
LMArena WebDev: ReactNot measured1352Only Qwen3.5-122B-A10B measured
LMArena WebDev: HTMLNot measured1352Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 34 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
AA Intelligence Index7.017.7Qwen3.5-122B-A10B
Epoch Capabilities Index127.3Not measuredOnly GPT-4 Turbo measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Agentic work benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
τ²-Bench TelecomNot measured93.6%Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 41 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
GPQA Diamond (Artificial Analysis run)Not measured85.7%Only Qwen3.5-122B-A10B measured
Humanity's Last Exam (Artificial Analysis run)3.1%25.2%Qwen3.5-122B-A10B
Mystery game puzzlesNot measured17.0%Only Qwen3.5-122B-A10B measured
LMArena Text: hard prompts12511421Qwen3.5-122B-A10B
LMArena Text: expert12231431Qwen3.5-122B-A10B
LMArena Text: hard prompts in English12661431Qwen3.5-122B-A10B
LMArena Vision: diagramsNot measured1249Only Qwen3.5-122B-A10B measured
LMArena Vision: homeworkNot measured1261Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
LMArena Text: math12721431Qwen3.5-122B-A10B
LMArena Text: mathematical work12681431Qwen3.5-122B-A10B
Neither model has a result on the other 12 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
LegalBench (Vals AI)80.5%Not measuredOnly GPT-4 Turbo measured
MedQA (Vals AI)82.0%Not measuredOnly GPT-4 Turbo measured
MMLU Pro (Artificial Analysis run)69.4%Not measuredOnly GPT-4 Turbo measured
MMLU81.3%Not measuredOnly GPT-4 Turbo measured
LMArena Text: science12561433Qwen3.5-122B-A10B
LMArena Text: medicine and healthcare12391423Qwen3.5-122B-A10B
LMArena Text: legal and government12651422Qwen3.5-122B-A10B
LMArena Text: business and finance12221414Qwen3.5-122B-A10B
Neither model has a result on the other 12 boards here
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Web design benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
Neither model has a result on 9 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index022
General benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
IFBenchNot measured75.7%Only Qwen3.5-122B-A10B measured
Long context reasoning (AA-LCR)Not measured76.3%Only Qwen3.5-122B-A10B measured
DTBench61.6%84.3%Qwen3.5-122B-A10B
LMCA9.8%32.2%Qwen3.5-122B-A10B
LMArena Text12721418Qwen3.5-122B-A10B
LMArena Text: instruction following12491400Qwen3.5-122B-A10B
LMArena Text: creative writing12681368Qwen3.5-122B-A10B
LMArena Vision10901244Qwen3.5-122B-A10B
LMArena Text: English12911428Qwen3.5-122B-A10B
LMArena Text: non-English12451401Qwen3.5-122B-A10B
LMArena Text: Chinese12421463Qwen3.5-122B-A10B
LMArena Text: German12591425Qwen3.5-122B-A10B
LMArena Text: Japanese11941367Qwen3.5-122B-A10B
LMArena Text: Korean11871353Qwen3.5-122B-A10B
LMArena Text: French12761443Qwen3.5-122B-A10B
LMArena Text: Spanish12601425Qwen3.5-122B-A10B
LMArena Text: Russian12591400Qwen3.5-122B-A10B
LMArena Text: Polish13021399Qwen3.5-122B-A10B
LMArena Text: multi-turn12671417Qwen3.5-122B-A10B
LMArena Text: longer queries12531411Qwen3.5-122B-A10B
LMArena Text: writing and language12791387Qwen3.5-122B-A10B
LMArena Text: entertainment and media12581366Qwen3.5-122B-A10B
LMArena Vision: English10971249Qwen3.5-122B-A10B
LMArena Vision: Chinese10451301Qwen3.5-122B-A10B
LMArena Vision: reading textNot measured1251Only Qwen3.5-122B-A10B measured
LMArena Vision: humorNot measured1243Only Qwen3.5-122B-A10B measured
LMArena Vision: creative writingNot measured1220Only Qwen3.5-122B-A10B measured
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4 Turbo and Qwen3.5-122B-A10B
BenchmarkGPT-4 TurboQwen3.5-122B-A10BLeader
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

GPT-4 Turbo$0.025Fits in one request
Qwen3.5-122B-A10B$0.0013Fits in one request

Qwen3.5-122B-A10B costs less

Repository review

50K input + 3K output tokens

GPT-4 Turbo$0.590Fits in one request
Qwen3.5-122B-A10B$0.019Fits in one request

Qwen3.5-122B-A10B costs less

Agent loop

200K input + 10K output tokens

GPT-4 Turbo$2.30Exceeds the context window
Qwen3.5-122B-A10B$0.073Fits in one request

Qwen3.5-122B-A10B 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 GPT-4 Turbo and Qwen3.5-122B-A10B
SpecificationOpenAI GPT-4 TurboQwen3.5-122B-A10B
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedApril 9, 2024February 25, 2026
Context window128K262K
Input $/Mtok$10.00$0.26
Output $/Mtok$30.00$2.08
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4 Turbo better than Qwen3.5-122B-A10B for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4 Turbo for work measured by AA Coding Index or LMArena Text: coding, where it leads.

Which is cheaper, GPT-4 Turbo or Qwen3.5-122B-A10B?

GPT-4 Turbo costs $10.00 per million input tokens and $30.00 per million output tokens; Qwen3.5-122B-A10B costs $0.26 and $2.08. Cost per solved task is known for neither of them.

Which has the bigger context window, GPT-4 Turbo or Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B, with 262K tokens against 128K.

How many benchmarks is the GPT-4 Turbo vs Qwen3.5-122B-A10B comparison based on?

36 benchmarks have a result for both models as of October 23, 2026. GPT-4 Turbo's coding index rests on 0 independent benchmarks and Qwen3.5-122B-A10B's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next