GPT-6.2 Sol vs MiMo-V2.5
GPT-6.2 Sol leads MiMo-V2.5 on coding, 83.1 to 50.0 on the Vibe Coding Index, and MiMo-V2.5 costs 5.0x less per output token ($2.00 vs $10.00 per million). Updated November 22, 2026; 28 benchmarks have a result for both.
GPT-6.2 Sol or MiMo-V2.5: which to pick
Pick GPT-6.2 Sol for coding: it scores 83.1 on the Vibe Coding Index against 50.0 for MiMo-V2.5.
Pick MiMo-V2.5 for output tokens 5.0x cheaper ($2.00 vs $10.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 28
- GPT-6.2 Sol only
- 28
- MiMo-V2.5 only
- 52
- 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.
Coding
Vibe Coding Index, six public coding benchmarks
GPT-6.2 Sol
GPT-6.2 Sol scores 83.1 against 50.0.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only GPT-6.2 Sol has a AA Intelligence Index result, 57.3.
Directional only
Reasoning
GPQA Diamond
No call
Only MiMo-V2.5 has a GPQA Diamond result, 81.6%.
Directional only
Knowledge
MMLU Pro
No call
Only MiMo-V2.5 has a MMLU Pro result, 82.9%.
Directional only
Web design
Design Arena: websites
No call
Only MiMo-V2.5 has a Design Arena: websites result, 1255.
Directional only
General
Vals Index
No call
Only GPT-6.2 Sol has a Vals Index result, 66.1%.
Directional only
Long documents
Listed context window
GPT-6.2 Sol
GPT-6.2 Sol takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.5
GPT-6.2 Sol $0.0070, MiMo-V2.5 $0.0014 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiMo-V2.5 has the number, $0.01.
Directional only
At a glance
- Coding index
- GPT-6.2 Sol 83.1 from 4 benchmarks, MiMo-V2.5 50.0 from 3 benchmarks.
- Widest category
- Coding, 36.1 points apart on average over 8 shared benchmarks.
- Widest single gap
- GameBench 2: GPT-6.2 Sol 94.4 against MiMo-V2.5 24.0, 70.4 points apart on a 0 to 100 scale.
- Output price
- GPT-6.2 Sol $10.00 against MiMo-V2.5 $2.00 per million output tokens, 5.0x apart.
- Context window
- GPT-6.2 Sol takes 1.05M tokens, MiMo-V2.5 1M.
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 | GPT-6.2 Sol | Bars | MiMo-V2.5 | Ties |
|---|---|---|---|---|
| Coding | 6 | 2 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 0 | 2 | ||
| Knowledge | 0 | 2 | ||
| Web design | 3 | 0 | ||
| General | 5 | 6 | ||
| All shared boards | 16 | 12 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index62
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | Leader |
|---|---|---|---|
| LiveBench coding | 83.7% | Not measured | Only GPT-6.2 Sol measured |
| LMArena WebDev | 1754 | 1438 | GPT-6.2 Sol |
| LiveCodeBench (Vals AI) | Not measured | 81.5% | Only MiMo-V2.5 measured |
| SWE-bench Verified (Vals AI) | Not measured | 71.0% | Only MiMo-V2.5 measured |
| Terminal-Bench 4 (Vals AI) | 60.6% | Not measured | Only GPT-6.2 Sol measured |
| Vibe Code Bench (Vals AI) | 87.6% | 42.2% | GPT-6.2 Sol |
| Code migration (Vals AI) | Not measured | 14.2% | Only MiMo-V2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 60.7% | Only MiMo-V2.5 measured |
| SciCode | Not measured | 43.9% | Only MiMo-V2.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 41.7% | Only MiMo-V2.5 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 60.1% | 0.0% | GPT-6.2 Sol |
| FrontierCode 2.0 | 44.4% | Not measured | Only GPT-6.2 Sol measured |
| ALE-Bench | Not measured | 514.0 | Only MiMo-V2.5 measured |
| LMArena Text: coding | 1440 | 1469 | MiMo-V2.5 |
| LMArena Text: software and IT | 1434 | 1464 | MiMo-V2.5 |
| LMArena WebDev: React | 1761 | 1423 | GPT-6.2 Sol |
| LMArena WebDev: HTML | 1840 | 1428 | GPT-6.2 Sol |
| GameBench 2 | 94.4 | 24.0 | GPT-6.2 Sol |
| Neither model has a result on the other 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 57.3 | Not measured | Only GPT-6.2 Sol measured |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | Leader |
|---|---|---|---|
| LiveBench research | 90.1% | Not measured | Only GPT-6.2 Sol measured |
| LiveBench browser | 88.2% | Not measured | Only GPT-6.2 Sol measured |
| LiveBench long agentic | 63.6% | Not measured | Only GPT-6.2 Sol measured |
| Finance Agent (Vals AI) | Not measured | 36.7% | Only MiMo-V2.5 measured |
| Tax Agent Bench (Vals AI) | 24.8% | 7.8% | GPT-6.2 Sol |
| Legal Research Bench (Vals AI) | 37.0% | 9.1% | GPT-6.2 Sol |
| Harvey's Legal Agent Benchmark (Vals AI) | 12.1% | Not measured | Only GPT-6.2 Sol measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 55.1% | Only MiMo-V2.5 measured |
| BioMysteryBench (Vals AI) | 77.8% | Not measured | Only GPT-6.2 Sol measured |
| Terminal-Bench-Science (Vals AI) | 58.6% | Not measured | Only GPT-6.2 Sol measured |
| Vals Science Index | 57.8% | Not measured | Only GPT-6.2 Sol measured |
| τ²-Bench Telecom | Not measured | 90.6% | Only MiMo-V2.5 measured |
| APEX-Agents | 66.6% | Not measured | Only GPT-6.2 Sol measured |
| LMArena Search | 1179 | Not measured | Only GPT-6.2 Sol measured |
| Toolathlon-Verified | Not measured | 49.1% | Only MiMo-V2.5 measured |
| Neither model has a result on the other 29 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 81.6% | Only MiMo-V2.5 measured |
| LiveBench reasoning | 90.6% | Not measured | Only GPT-6.2 Sol measured |
| MysteryMechanism (Vals AI) | 36.9% | Not measured | Only GPT-6.2 Sol measured |
| MMMU Pro (Vals AI) | Not measured | 80.0% | Only MiMo-V2.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 84.9% | Only MiMo-V2.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 27.2% | Only MiMo-V2.5 measured |
| HLE-Diamond (Artificial Analysis run) | 64.0% | Not measured | Only GPT-6.2 Sol measured |
| CritPt v2, hard subset (Artificial Analysis run) | 64.0% | Not measured | Only GPT-6.2 Sol measured |
| ARC-AGI | 97.5% | Not measured | Only GPT-6.2 Sol measured |
| ARC-AGI-2 | 85.8% | Not measured | Only GPT-6.2 Sol measured |
| SimpleBench | 69.9% | Not measured | Only GPT-6.2 Sol measured |
| LMArena Text: hard prompts | 1419 | 1450 | MiMo-V2.5 |
| LMArena Text: expert | Not measured | 1459 | Only MiMo-V2.5 measured |
| LMArena Text: hard prompts in English | 1413 | 1461 | MiMo-V2.5 |
| LMArena Vision: diagrams | Not measured | 1270 | Only MiMo-V2.5 measured |
| LMArena Vision: homework | Not measured | 1261 | Only MiMo-V2.5 measured |
| Kagi LLM Benchmark | 67.0% | Not measured | Only GPT-6.2 Sol measured |
| Humanity's Last Exam (Scale run) | 56.5% | Not measured | Only GPT-6.2 Sol measured |
| Neither model has a result on the other 8 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | Leader |
|---|---|---|---|
| ProofBench | Not measured | 16.0% | Only MiMo-V2.5 measured |
| LMArena Text: math | Not measured | 1435 | Only MiMo-V2.5 measured |
| LMArena Text: mathematical work | Not measured | 1449 | Only MiMo-V2.5 measured |
| MathArena | 91.2% | Not measured | Only GPT-6.2 Sol measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 82.9% | Only MiMo-V2.5 measured |
| LegalBench (Vals AI) | Not measured | 78.9% | Only MiMo-V2.5 measured |
| CorpFin (Vals AI) | Not measured | 59.9% | Only MiMo-V2.5 measured |
| TaxEval (Vals AI) | Not measured | 71.8% | Only MiMo-V2.5 measured |
| MortgageTax (Vals AI) | Not measured | 59.3% | Only MiMo-V2.5 measured |
| MedCode (Vals AI) | Not measured | 31.9% | Only MiMo-V2.5 measured |
| AA-Omniscience | 40.4 | Not measured | Only GPT-6.2 Sol measured |
| LMArena Text: science | 1432 | 1439 | MiMo-V2.5 |
| LMArena Text: medicine and healthcare | Not measured | 1432 | Only MiMo-V2.5 measured |
| LMArena Text: legal and government | Not measured | 1424 | Only MiMo-V2.5 measured |
| LMArena Text: business and finance | 1383 | 1432 | MiMo-V2.5 |
| Neither model has a result on the other 10 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1255 | Only MiMo-V2.5 measured |
| Design Arena: UI components | Not measured | 1242 | Only MiMo-V2.5 measured |
| Design Arena: game dev | 1437 | 1225 | GPT-6.2 Sol |
| Design Arena: data viz | Not measured | 1246 | Only MiMo-V2.5 measured |
| Design Arena: 3D | 1482 | 1185 | GPT-6.2 Sol |
| Design Arena: all code categories | 1405 | 1244 | GPT-6.2 Sol |
| Design Arena: SVG | Not measured | 1173 | Only MiMo-V2.5 measured |
| Design Arena: ASCII art | Not measured | 1128 | Only MiMo-V2.5 measured |
| LiveBench design | 80.0% | Not measured | Only GPT-6.2 Sol measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index56
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | Leader |
|---|---|---|---|
| Vals Index | 66.1% | Not measured | Only GPT-6.2 Sol measured |
| LiveBench data analysis | 81.1% | Not measured | Only GPT-6.2 Sol measured |
| MedScribe (Vals AI) | Not measured | 72.2% | Only MiMo-V2.5 measured |
| Vals Multimodal Index | Not measured | 52.8% | Only MiMo-V2.5 measured |
| IFBench | Not measured | 67.1% | Only MiMo-V2.5 measured |
| Long context reasoning (AA-LCR) | Not measured | 73.0% | Only MiMo-V2.5 measured |
| GDPval-AA | Not measured | 1004 | Only MiMo-V2.5 measured |
| LMArena Text | 1414 | 1428 | MiMo-V2.5 |
| LMArena Text: instruction following | 1434 | 1434 | MiMo-V2.5 |
| LMArena Text: creative writing | 1403 | 1391 | GPT-6.2 Sol |
| LMArena Vision | Not measured | 1247 | Only MiMo-V2.5 measured |
| LMArena Text: English | 1419 | 1447 | MiMo-V2.5 |
| LMArena Text: non-English | 1405 | 1404 | GPT-6.2 Sol |
| LMArena Text: Chinese | 1434 | 1471 | MiMo-V2.5 |
| LMArena Text: German | Not measured | 1419 | Only MiMo-V2.5 measured |
| LMArena Text: Japanese | Not measured | 1307 | Only MiMo-V2.5 measured |
| LMArena Text: Korean | Not measured | 1356 | Only MiMo-V2.5 measured |
| LMArena Text: French | Not measured | 1450 | Only MiMo-V2.5 measured |
| LMArena Text: Spanish | Not measured | 1416 | Only MiMo-V2.5 measured |
| LMArena Text: Russian | 1401 | 1395 | GPT-6.2 Sol |
| LMArena Text: Polish | Not measured | 1410 | Only MiMo-V2.5 measured |
| LMArena Text: multi-turn | 1420 | 1445 | MiMo-V2.5 |
| LMArena Text: longer queries | 1427 | 1445 | MiMo-V2.5 |
| LMArena Text: writing and language | 1420 | 1408 | GPT-6.2 Sol |
| LMArena Text: entertainment and media | 1408 | 1399 | GPT-6.2 Sol |
| LMArena Vision: English | Not measured | 1260 | Only MiMo-V2.5 measured |
| LMArena Vision: Chinese | Not measured | 1322 | Only MiMo-V2.5 measured |
| LMArena Vision: reading text | Not measured | 1256 | Only MiMo-V2.5 measured |
| LMArena Vision: humor | Not measured | 1227 | Only MiMo-V2.5 measured |
| LMArena Vision: recognizing things | Not measured | 1195 | Only MiMo-V2.5 measured |
| LMArena Vision: creative writing | Not measured | 1230 | Only MiMo-V2.5 measured |
| MultiChallenge | 72.0% | Not measured | Only GPT-6.2 Sol measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-6.2 Sol | MiMo-V2.5 | 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
MiMo-V2.5 costs less
Repository review
50K input + 3K output tokens
MiMo-V2.5 costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.5 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 | OpenAI GPT-6.2 Sol | Xiaomi MiMo-V2.5 |
|---|---|---|
| Maker | OpenAI | Xiaomi |
| Weights | No public weights listed | Open weights |
| Released | November 17, 2026 | April 22, 2026 |
| Context window | 1.05M | 1M |
| Input $/Mtok | $2.00 | $0.40 |
| Output $/Mtok | $10.00 | $2.00 |
| Coding index | 83.1 | 50.0 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | Not computable | $0.01 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-6.2 Sol better than MiMo-V2.5 for coding?
Pick GPT-6.2 Sol for coding: it scores 83.1 on the Vibe Coding Index against 50.0 for MiMo-V2.5. Pick MiMo-V2.5 for output tokens 5.0x cheaper ($2.00 vs $10.00 per million) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, GPT-6.2 Sol or MiMo-V2.5?
GPT-6.2 Sol costs $2.00 per million input tokens and $10.00 per million output tokens; MiMo-V2.5 costs $0.40 and $2.00. Cost per solved task is known for MiMo-V2.5 only.
Which has the bigger context window, GPT-6.2 Sol or MiMo-V2.5?
GPT-6.2 Sol, with 1.05M tokens against 1M.
How many benchmarks is the GPT-6.2 Sol vs MiMo-V2.5 comparison based on?
28 benchmarks have a result for both models as of November 22, 2026. GPT-6.2 Sol's coding index rests on 4 independent benchmarks and MiMo-V2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.