UI-TARS 7B vs Gemini 2.5 Pro
UI-TARS 7B costs 50.0x less per output token than Gemini 2.5 Pro ($0.20 vs $10.00 per million). Updated October 22, 2026; 1 benchmarks have a result for both.
UI-TARS 7B or Gemini 2.5 Pro: which to pick
Only Gemini 2.5 Pro has a coding score, 19.1 on the Vibe Coding Index; UI-TARS 7B has none, so the two cannot be ranked on coding.
Pick UI-TARS 7B for output tokens 50.0x cheaper ($0.20 vs $10.00 per million).
- Shared results
- 1
- UI-TARS 7B only
- 0
- Gemini 2.5 Pro only
- 89
- Like-for-like categories
- 1 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Gemini 2.5 Pro has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Gemini 2.5 Pro has a AA Intelligence Index result, 16.1.
Directional only
Agentic work
AA Agentic Index
No call
Only Gemini 2.5 Pro has a AA Agentic Index result, 1.6.
Directional only
Web design
Design Arena: websites
No call
Only Gemini 2.5 Pro has a Design Arena: websites result, 1167.
Directional only
Long documents
Listed context window
Gemini 2.5 Pro
Gemini 2.5 Pro takes 1.05M tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
UI-TARS 7B
UI-TARS 7B $0.0002, Gemini 2.5 Pro $0.0063 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Gemini 2.5 Pro has the number, $0.64.
Directional only
At a glance
- Coding index
- UI-TARS 7B not benchmarked, Gemini 2.5 Pro 19.1 from 3 benchmarks.
- Widest category
- Reasoning, 49.6 points apart on average over 1 shared benchmark.
- Widest single gap
- Kagi LLM Benchmark: UI-TARS 7B 20.7% against Gemini 2.5 Pro 70.3%, 49.6 points apart on a 0 to 100 scale.
- Output price
- UI-TARS 7B $0.20 against Gemini 2.5 Pro $10.00 per million output tokens, 50.0x apart.
- Context window
- UI-TARS 7B takes 128K tokens, Gemini 2.5 Pro 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.
| Category | UI-TARS 7B | Bars | Gemini 2.5 Pro | Ties |
|---|---|---|---|---|
| Reasoning | 0 | 1 | ||
| All shared boards | 0 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index15 boards, none shared
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 53.6% | Only Gemini 2.5 Pro measured |
| LMArena WebDev | Not measured | 1226 | Only Gemini 2.5 Pro measured |
| AA Coding Index | Not measured | 33.3 | Only Gemini 2.5 Pro measured |
| SWE-bench Verified (Vals AI) | Not measured | 54.4% | Only Gemini 2.5 Pro measured |
| Vibe Code Bench (Vals AI) | Not measured | 0.4% | Only Gemini 2.5 Pro measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 80.1% | Only Gemini 2.5 Pro measured |
| SciCode | Not measured | 46.3% | Only Gemini 2.5 Pro measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 26.5% | Only Gemini 2.5 Pro measured |
| Terminal-Bench | Not measured | 32.6% | Only Gemini 2.5 Pro measured |
| GSO-Bench | Not measured | 3.9% | Only Gemini 2.5 Pro measured |
| WeirdML | Not measured | 54.0% | Only Gemini 2.5 Pro measured |
| LMArena Text: coding | Not measured | 1452 | Only Gemini 2.5 Pro measured |
| LMArena Text: software and IT | Not measured | 1459 | Only Gemini 2.5 Pro measured |
| LMArena WebDev: HTML | Not measured | 1235 | Only Gemini 2.5 Pro measured |
| LMArena WebDev: from an image | Not measured | 1285 | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 16.1 | Only Gemini 2.5 Pro measured |
| Epoch Capabilities Index | Not measured | 145.1 | Only Gemini 2.5 Pro measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.6 | Only Gemini 2.5 Pro measured |
| τ²-Bench Telecom | Not measured | 54.1% | Only Gemini 2.5 Pro measured |
| GDPval | Not measured | 23.3% | Only Gemini 2.5 Pro measured |
| DeepResearch Bench | Not measured | 41.5% | Only Gemini 2.5 Pro measured |
| Vending-Bench 2 | Not measured | $574 | Only Gemini 2.5 Pro measured |
| BrowseComp-Plus | Not measured | 29.5% | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 84.4% | Only Gemini 2.5 Pro measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 22.5% | Only Gemini 2.5 Pro measured |
| GPQA Diamond (Epoch AI run) | Not measured | 85.3% | Only Gemini 2.5 Pro measured |
| ARC-AGI | Not measured | 41.0% | Only Gemini 2.5 Pro measured |
| ARC-AGI-2 | Not measured | 4.9% | Only Gemini 2.5 Pro measured |
| LMArena Text: hard prompts | Not measured | 1455 | Only Gemini 2.5 Pro measured |
| LMArena Text: expert | Not measured | 1452 | Only Gemini 2.5 Pro measured |
| LMArena Text: hard prompts in English | Not measured | 1453 | Only Gemini 2.5 Pro measured |
| LMArena Vision: diagrams | Not measured | 1274 | Only Gemini 2.5 Pro measured |
| LMArena Vision: homework | Not measured | 1281 | Only Gemini 2.5 Pro measured |
| Kagi LLM Benchmark | 20.7% | 70.3% | Gemini 2.5 Pro |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 87.7 | Only Gemini 2.5 Pro measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 87.7% | Only Gemini 2.5 Pro measured |
| OTIS Mock AIME | Not measured | 84.7% | Only Gemini 2.5 Pro measured |
| FrontierMath, tiers 1 to 3 | Not measured | 24.6% | Only Gemini 2.5 Pro measured |
| FrontierMath, tier 4 | Not measured | 0.0% | Only Gemini 2.5 Pro measured |
| LMArena Text: math | Not measured | 1450 | Only Gemini 2.5 Pro measured |
| LMArena Text: mathematical work | Not measured | 1454 | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| CaseLaw (Vals AI) | Not measured | 63.9% | Only Gemini 2.5 Pro measured |
| CorpFin (Vals AI) | Not measured | 60.8% | Only Gemini 2.5 Pro measured |
| MortgageTax (Vals AI) | Not measured | 68.9% | Only Gemini 2.5 Pro measured |
| MedCode (Vals AI) | Not measured | 50.6% | Only Gemini 2.5 Pro measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 86.2% | Only Gemini 2.5 Pro measured |
| LMArena Text: science | Not measured | 1480 | Only Gemini 2.5 Pro measured |
| LMArena Text: medicine and healthcare | Not measured | 1476 | Only Gemini 2.5 Pro measured |
| LMArena Text: legal and government | Not measured | 1480 | Only Gemini 2.5 Pro measured |
| LMArena Text: business and finance | Not measured | 1439 | Only Gemini 2.5 Pro measured |
| FACTS Benchmark Suite | Not measured | 61.5% | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 8 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1167 | Only Gemini 2.5 Pro measured |
| Design Arena: UI components | Not measured | 1137 | Only Gemini 2.5 Pro measured |
| Design Arena: game dev | Not measured | 1111 | Only Gemini 2.5 Pro measured |
| Design Arena: data viz | Not measured | 1222 | Only Gemini 2.5 Pro measured |
| Design Arena: 3D | Not measured | 1080 | Only Gemini 2.5 Pro measured |
| Design Arena: all code categories | Not measured | 1152 | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index33 boards, none shared
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 41.9% | Only Gemini 2.5 Pro measured |
| MedScribe (Vals AI) | Not measured | 73.5% | Only Gemini 2.5 Pro measured |
| IFBench | Not measured | 48.7% | Only Gemini 2.5 Pro measured |
| Long context reasoning (AA-LCR) | Not measured | 69.0% | Only Gemini 2.5 Pro measured |
| DTBench | Not measured | 82.4% | Only Gemini 2.5 Pro measured |
| LMCA | Not measured | 34.8% | Only Gemini 2.5 Pro measured |
| Creative writing (Lech Mazur) | Not measured | 83.8% | Only Gemini 2.5 Pro measured |
| LMArena Text | Not measured | 1458 | Only Gemini 2.5 Pro measured |
| LMArena Text: instruction following | Not measured | 1437 | Only Gemini 2.5 Pro measured |
| LMArena Text: creative writing | Not measured | 1454 | Only Gemini 2.5 Pro measured |
| LMArena Vision | Not measured | 1263 | Only Gemini 2.5 Pro measured |
| LMArena Text: English | Not measured | 1458 | Only Gemini 2.5 Pro measured |
| LMArena Text: non-English | Not measured | 1452 | Only Gemini 2.5 Pro measured |
| LMArena Text: Chinese | Not measured | 1507 | Only Gemini 2.5 Pro measured |
| LMArena Text: German | Not measured | 1487 | Only Gemini 2.5 Pro measured |
| LMArena Text: Japanese | Not measured | 1461 | Only Gemini 2.5 Pro measured |
| LMArena Text: Korean | Not measured | 1434 | Only Gemini 2.5 Pro measured |
| LMArena Text: French | Not measured | 1473 | Only Gemini 2.5 Pro measured |
| LMArena Text: Spanish | Not measured | 1474 | Only Gemini 2.5 Pro measured |
| LMArena Text: Russian | Not measured | 1461 | Only Gemini 2.5 Pro measured |
| LMArena Text: Polish | Not measured | 1479 | Only Gemini 2.5 Pro measured |
| LMArena Text: multi-turn | Not measured | 1453 | Only Gemini 2.5 Pro measured |
| LMArena Text: longer queries | Not measured | 1449 | Only Gemini 2.5 Pro measured |
| LMArena Text: writing and language | Not measured | 1454 | Only Gemini 2.5 Pro measured |
| LMArena Text: entertainment and media | Not measured | 1441 | Only Gemini 2.5 Pro measured |
| LMArena Vision: English | Not measured | 1261 | Only Gemini 2.5 Pro measured |
| LMArena Vision: Chinese | Not measured | 1300 | Only Gemini 2.5 Pro measured |
| LMArena Vision: reading text | Not measured | 1270 | Only Gemini 2.5 Pro measured |
| LMArena Vision: humor | Not measured | 1262 | Only Gemini 2.5 Pro measured |
| LMArena Vision: captioning | Not measured | 1304 | Only Gemini 2.5 Pro measured |
| LMArena Vision: recognizing things | Not measured | 1283 | Only Gemini 2.5 Pro measured |
| LMArena Vision: creative writing | Not measured | 1265 | Only Gemini 2.5 Pro measured |
| LMArena Document | Not measured | 1421 | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | UI-TARS 7B | Gemini 2.5 Pro | Leader |
|---|---|---|---|
| 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
UI-TARS 7B costs less
Repository review
50K input + 3K output tokens
UI-TARS 7B costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | ByteDance UI-TARS 7B | Google Gemini 2.5 Pro |
|---|---|---|
| Maker | ByteDance | |
| Weights | Open weights | No public weights listed |
| Released | July 22, 2025 | June 17, 2025 |
| Context window | 128K | 1.05M |
| Input $/Mtok | $0.10 | $1.25 |
| Output $/Mtok | $0.20 | $10.00 |
| Coding index | Not benchmarked | 19.1 |
| Independent measurements behind it | 0 | 3 |
| Cost per solved task | Not computable | $0.64 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is UI-TARS 7B better than Gemini 2.5 Pro for coding?
Only Gemini 2.5 Pro has a coding score, 19.1 on the Vibe Coding Index; UI-TARS 7B has none, so the two cannot be ranked on coding. Pick UI-TARS 7B for output tokens 50.0x cheaper ($0.20 vs $10.00 per million).
Which is cheaper, UI-TARS 7B or Gemini 2.5 Pro?
UI-TARS 7B costs $0.10 per million input tokens and $0.20 per million output tokens; Gemini 2.5 Pro costs $1.25 and $10.00. Cost per solved task is known for Gemini 2.5 Pro only.
Which has the bigger context window, UI-TARS 7B or Gemini 2.5 Pro?
Gemini 2.5 Pro, with 1.05M tokens against 128K.
How many benchmarks is the UI-TARS 7B vs Gemini 2.5 Pro comparison based on?
1 benchmarks have a result for both models as of October 22, 2026. UI-TARS 7B's coding index rests on 0 independent benchmarks and Gemini 2.5 Pro's on 3. Where only one model has a result, the page says so instead of naming a winner.