Enter opens the highlighted result. Esc closes.

UI-TARS 7B vs Qwen3.8 2.4T A95B

UI-TARS 7B costs 30.0x less per output token than Qwen3.8 2.4T A95B ($0.20 vs $6.00 per million). Updated October 23, 2026; no benchmark has tested both models yet.

Replace UI-TARS 7B Replace Qwen3.8 2.4T A95B
UI-TARS 7BByteDance
Coding
No data
Overall
No data
Output $/M
$0.20
Qwen3.8 2.4T A95BQwen
Coding
No data
Overall
No data
Output $/M
$6.00
vs $0.20 vs $6.00 per 1M output tokens. UI-TARS 7B is 30.0x cheaper.

UI-TARS 7B 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 UI-TARS 7B for output tokens 30.0x cheaper ($0.20 vs $6.00 per million).

Model AUI-TARS 7BByteDanceNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen3.8 2.4T A95BQwenNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. UI-TARS 7B has results on Kagi LLM Benchmark; Qwen3.8 2.4T A95B on AA Coding Index, SciCode and AA Intelligence Index. Compare them on price and context instead.

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
UI-TARS 7B not benchmarked, Qwen3.8 2.4T A95B not benchmarked.
Widest category
None yet: no category has been tested on both models.
Widest single gap
None yet: no benchmark has tested both models.
Output price
UI-TARS 7B $0.20 against Qwen3.8 2.4T A95B $6.00 per million output tokens, 30.0x apart.
Context window
UI-TARS 7B takes 128K tokens, Qwen3.8 2.4T A95B 1.05M.

Benchmark by benchmark

Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.

CodingDirectional onlySix of these boards feed the Vibe Coding Index2 boards measured
Coding benchmarks for UI-TARS 7B and Qwen3.8 2.4T A95B
BenchmarkUI-TARS 7BQwen3.8 2.4T A95BLeader
AA Coding IndexNot measured71.9Only Qwen3.8 2.4T A95B measured
SciCodeNot measured54.1%Only Qwen3.8 2.4T A95B measured
Neither model has a result on the other 41 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Intelligence benchmarks for UI-TARS 7B and Qwen3.8 2.4T A95B
BenchmarkUI-TARS 7BQwen3.8 2.4T A95BLeader
AA Intelligence IndexNot measured39.9Only Qwen3.8 2.4T A95B measured
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
Agentic work benchmarks for UI-TARS 7B and Qwen3.8 2.4T A95B
BenchmarkUI-TARS 7BQwen3.8 2.4T A95BLeader
AA Agentic IndexNot measured50.1Only Qwen3.8 2.4T A95B measured
MCP AtlasNot measured84.5%Only Qwen3.8 2.4T A95B measured
Neither model has a result on the other 40 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
Reasoning benchmarks for UI-TARS 7B and Qwen3.8 2.4T A95B
BenchmarkUI-TARS 7BQwen3.8 2.4T A95BLeader
GPQA Diamond (Artificial Analysis run)Not measured93.5%Only Qwen3.8 2.4T A95B measured
Humanity's Last Exam (Artificial Analysis run)Not measured42.4%Only Qwen3.8 2.4T A95B measured
Kagi LLM Benchmark20.7%Not measuredOnly UI-TARS 7B measured
Neither model has a result on the other 20 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Math benchmarks for UI-TARS 7B and Qwen3.8 2.4T A95B
BenchmarkUI-TARS 7BQwen3.8 2.4T A95BLeader
MathArenaNot measured31.6%Only Qwen3.8 2.4T A95B measured
Neither model has a result on the other 13 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
General benchmarks for UI-TARS 7B and Qwen3.8 2.4T A95B
BenchmarkUI-TARS 7BQwen3.8 2.4T A95BLeader
Long context reasoning (AA-LCR)Not measured80.3%Only Qwen3.8 2.4T A95B measured
Neither model has a result on the other 47 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

UI-TARS 7B$0.0002Fits in one request
Qwen3.8 2.4T A95B$0.0050Fits in one request

UI-TARS 7B costs less

Repository review

50K input + 3K output tokens

UI-TARS 7B$0.0056Fits in one request
Qwen3.8 2.4T A95B$0.118Fits in one request

UI-TARS 7B costs less

Agent loop

200K input + 10K output tokens

UI-TARS 7B$0.022Exceeds the context window
Qwen3.8 2.4T A95B$0.460Fits in one request

UI-TARS 7B 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 UI-TARS 7B and Qwen3.8 2.4T A95B
SpecificationByteDance UI-TARS 7BQwen3.8 2.4T A95B
MakerByteDanceQwen
WeightsOpen weightsOpen weights
ReleasedJuly 22, 2025August 12, 2026
Context window128K1.05M
Input $/Mtok$0.10$2.00
Output $/Mtok$0.20$6.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is UI-TARS 7B 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 UI-TARS 7B for output tokens 30.0x cheaper ($0.20 vs $6.00 per million).

Which is cheaper, UI-TARS 7B or Qwen3.8 2.4T A95B?

UI-TARS 7B costs $0.10 per million input tokens and $0.20 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, UI-TARS 7B or Qwen3.8 2.4T A95B?

Qwen3.8 2.4T A95B, with 1.05M tokens against 128K.

Has any benchmark tested both UI-TARS 7B and Qwen3.8 2.4T A95B?

No benchmark has tested both yet. UI-TARS 7B has results on Kagi LLM Benchmark; Qwen3.8 2.4T A95B on AA Coding Index, SciCode and AA Intelligence Index. Compare them on price and context instead. Data as of October 23, 2026.

Compare next