GPT-5.2 vs MiMo-V2.5
GPT-5.2 leads MiMo-V2.5 on coding, 55.9 to 50.0 on the Vibe Coding Index, and MiMo-V2.5 costs 41.7x less per output token ($0.336 vs $14.00 per million). Updated October 22, 2026; 69 benchmarks have a result for both.
GPT-5.2 or MiMo-V2.5: which to pick
Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 50.0 for MiMo-V2.5.
Pick MiMo-V2.5 for output tokens 41.7x cheaper ($0.336 vs $14.00 per million) and a lower cost per solved task ($0.01 against $1.91).
- Shared results
- 69
- GPT-5.2 only
- 45
- MiMo-V2.5 only
- 11
- Like-for-like categories
- 8 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-5.2
GPT-5.2 scores 55.9 against 50.0.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-5.2
GPT-5.2 leads, 30.4 against 21.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only MiMo-V2.5 has a AA Agentic Index result, 15.8.
Directional only
Reasoning
GPQA Diamond
GPT-5.2
GPT-5.2 leads, 91.7% against 81.6%.
Same board, both measured
Math
AIME
No call
Only GPT-5.2 has a AIME result, 96.9%.
Directional only
Knowledge
MMLU Pro
GPT-5.2
GPT-5.2 leads, 86.2% against 82.9%.
Same board, both measured
Web design
Design Arena: websites
MiMo-V2.5
MiMo-V2.5 leads, 1265 against 1195.
Same board, both measured
Long documents
Listed context window
MiMo-V2.5
MiMo-V2.5 takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.5
GPT-5.2 $0.0088, MiMo-V2.5 $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiMo-V2.5
GPT-5.2 $1.91, MiMo-V2.5 $0.01.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.2 55.9 from 3 benchmarks, MiMo-V2.5 50.0 from 3 benchmarks.
- Widest category
- Intelligence, 8.6 points apart on average over 1 shared benchmark.
- Widest single gap
- ALE-Bench: GPT-5.2 1293.5 against MiMo-V2.5 514.0, 26.0 points apart on a 0 to 100 scale.
- Output price
- GPT-5.2 $14.00 against MiMo-V2.5 $0.336 per million output tokens, 41.7x apart.
- Context window
- GPT-5.2 takes 400K tokens, MiMo-V2.5 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 | GPT-5.2 | Bars | MiMo-V2.5 | Ties |
|---|---|---|---|---|
| Coding | 5 | 4 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 5 | 4 | ||
| Math | 1 | 2 | ||
| Knowledge | 7 | 3 | ||
| Web design | 1 | 7 | ||
| General | 14 | 14 | ||
| All shared boards | 34 | 35 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index54
| Benchmark | GPT-5.2 | MiMo-V2.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | 72.8% | Not measured | Only GPT-5.2 measured |
| SWE-bench Multilingual | 66.7% | Not measured | Only GPT-5.2 measured |
| LMArena WebDev | 1417 | 1438 | MiMo-V2.5 |
| AA Coding Index | Not measured | 56.8 | Only MiMo-V2.5 measured |
| LiveCodeBench (Vals AI) | 85.4% | 81.5% | GPT-5.2 |
| SWE-bench Verified (Vals AI) | 75.8% | 71.0% | GPT-5.2 |
| Vibe Code Bench (Vals AI) | 53.5% | 42.2% | GPT-5.2 |
| 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 |
| LiveCodeBench (Artificial Analysis run) | 89.4% | Not measured | Only GPT-5.2 measured |
| SciCode | Not measured | 43.9% | Only MiMo-V2.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 41.7% | GPT-5.2 |
| Terminal-Bench | 64.9% | Not measured | Only GPT-5.2 measured |
| GSO-Bench | 27.5% | Not measured | Only GPT-5.2 measured |
| WeirdML | 72.2% | Not measured | Only GPT-5.2 measured |
| ALE-Bench | 1293.5 | 514.0 | GPT-5.2 |
| LMArena Text: coding | 1442 | 1469 | MiMo-V2.5 |
| LMArena Text: software and IT | 1434 | 1463 | MiMo-V2.5 |
| LMArena WebDev: React | Not measured | 1425 | Only MiMo-V2.5 measured |
| LMArena WebDev: HTML | 1427 | 1429 | MiMo-V2.5 |
| Neither model has a result on the other 19 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.2 | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 21.8 | GPT-5.2 |
| Epoch Capabilities Index | 153.7 | Not measured | Only GPT-5.2 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5.2 | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 15.8 | Only MiMo-V2.5 measured |
| Design Arena: agents building web apps | 1086 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building full-stack apps | 1043 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building mobile apps | 1093 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Android apps | 1059 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Godot games | 1142 | Not measured | Only GPT-5.2 measured |
| Finance Agent (Vals AI) | Not measured | 36.7% | Only MiMo-V2.5 measured |
| Tax Agent Bench (Vals AI) | Not measured | 7.8% | Only MiMo-V2.5 measured |
| Legal Research Bench (Vals AI) | Not measured | 9.1% | Only MiMo-V2.5 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 55.1% | Only MiMo-V2.5 measured |
| τ²-Bench Telecom | 84.8% | 90.6% | MiMo-V2.5 |
| METR time horizons | 75.3% | Not measured | Only GPT-5.2 measured |
| Remote Labor Index | 2.5% | Not measured | Only GPT-5.2 measured |
| GDPval | 49.7% | Not measured | Only GPT-5.2 measured |
| DeepResearch Bench | 41.1% | Not measured | Only GPT-5.2 measured |
| Vending-Bench 2 | $3,591 | Not measured | Only GPT-5.2 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 55.9% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index54
| Benchmark | GPT-5.2 | MiMo-V2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 91.7% | 81.6% | GPT-5.2 |
| MMMU Pro (Vals AI) | 86.7% | 80.0% | GPT-5.2 |
| GPQA Diamond (Artificial Analysis run) | 90.3% | 84.9% | GPT-5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 37.7% | 27.2% | GPT-5.2 |
| GPQA Diamond (Epoch AI run) | 91.4% | Not measured | Only GPT-5.2 measured |
| ARC-AGI | 86.2% | Not measured | Only GPT-5.2 measured |
| ARC-AGI-2 | 52.9% | Not measured | Only GPT-5.2 measured |
| SimpleBench | 45.8% | Not measured | Only GPT-5.2 measured |
| Chess puzzles | 48.0% | Not measured | Only GPT-5.2 measured |
| Mystery game puzzles | 23.0% | Not measured | Only GPT-5.2 measured |
| EBR-bench | 23.0% | Not measured | Only GPT-5.2 measured |
| VPCT | 84.0% | Not measured | Only GPT-5.2 measured |
| LMArena Text: hard prompts | 1428 | 1450 | MiMo-V2.5 |
| LMArena Text: expert | 1445 | 1459 | MiMo-V2.5 |
| LMArena Text: hard prompts in English | 1431 | 1461 | MiMo-V2.5 |
| LMArena Vision: diagrams | 1265 | 1269 | MiMo-V2.5 |
| LMArena Vision: homework | 1276 | 1262 | GPT-5.2 |
| Kagi LLM Benchmark | 73.3% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | GPT-5.2 | MiMo-V2.5 | Leader |
|---|---|---|---|
| AIME | 96.9% | Not measured | Only GPT-5.2 measured |
| MGSM (Vals AI) | 94.0% | Not measured | Only GPT-5.2 measured |
| AA Math Index | 99.0 | Not measured | Only GPT-5.2 measured |
| AIME 2025 (Artificial Analysis run) | 99.0% | Not measured | Only GPT-5.2 measured |
| OTIS Mock AIME | 96.1% | Not measured | Only GPT-5.2 measured |
| FrontierMath, tiers 1 to 3 | 67.4% | Not measured | Only GPT-5.2 measured |
| FrontierMath, tier 4 | 31.7% | Not measured | Only GPT-5.2 measured |
| ProofBench | 15.0% | 16.0% | MiMo-V2.5 |
| LMArena Text: math | 1440 | 1436 | GPT-5.2 |
| LMArena Text: mathematical work | 1442 | 1451 | MiMo-V2.5 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index73
| Benchmark | GPT-5.2 | MiMo-V2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 82.9% | GPT-5.2 |
| LegalBench (Vals AI) | 82.8% | 78.9% | GPT-5.2 |
| CaseLaw (Vals AI) | 66.0% | Not measured | Only GPT-5.2 measured |
| CorpFin (Vals AI) | 65.9% | 59.9% | GPT-5.2 |
| TaxEval (Vals AI) | 75.8% | 71.8% | GPT-5.2 |
| MortgageTax (Vals AI) | 67.1% | 59.3% | GPT-5.2 |
| MedQA (Vals AI) | 94.1% | Not measured | Only GPT-5.2 measured |
| MedCode (Vals AI) | 49.8% | 31.9% | GPT-5.2 |
| MMLU Pro (Artificial Analysis run) | 87.4% | Not measured | Only GPT-5.2 measured |
| SimpleQA Verified | 37.1% | Not measured | Only GPT-5.2 measured |
| LMArena Text: science | 1425 | 1440 | MiMo-V2.5 |
| LMArena Text: medicine and healthcare | 1425 | 1432 | MiMo-V2.5 |
| LMArena Text: legal and government | 1427 | 1425 | GPT-5.2 |
| LMArena Text: business and finance | 1414 | 1432 | MiMo-V2.5 |
| FACTS Benchmark Suite | 48.5% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index17
| Benchmark | GPT-5.2 | MiMo-V2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1195 | 1265 | MiMo-V2.5 |
| Design Arena: UI components | 1190 | 1255 | MiMo-V2.5 |
| Design Arena: game dev | 1195 | 1249 | MiMo-V2.5 |
| Design Arena: data viz | 1202 | 1250 | MiMo-V2.5 |
| Design Arena: 3D | 1079 | 1215 | MiMo-V2.5 |
| Design Arena: all code categories | 1170 | 1260 | MiMo-V2.5 |
| Design Arena: SVG | 1139 | 1179 | MiMo-V2.5 |
| Design Arena: ASCII art | 1152 | 1140 | GPT-5.2 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index1414
| Benchmark | GPT-5.2 | MiMo-V2.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 49.3% | 43.3% | GPT-5.2 |
| MedScribe (Vals AI) | 84.4% | 72.2% | GPT-5.2 |
| Vals Multimodal Index | Not measured | 52.8% | Only MiMo-V2.5 measured |
| IFBench | 75.4% | 67.1% | GPT-5.2 |
| Long context reasoning (AA-LCR) | 82.7% | 73.0% | GPT-5.2 |
| DTBench | 90.9% | Not measured | Only GPT-5.2 measured |
| LMCA | 43.9% | Not measured | Only GPT-5.2 measured |
| CL-bench | 18.2% | Not measured | Only GPT-5.2 measured |
| Furniture assembly | 38.3% | Not measured | Only GPT-5.2 measured |
| LMArena Text | 1416 | 1428 | MiMo-V2.5 |
| LMArena Text: instruction following | 1409 | 1435 | MiMo-V2.5 |
| LMArena Text: creative writing | 1376 | 1393 | MiMo-V2.5 |
| LMArena Vision | 1246 | 1247 | MiMo-V2.5 |
| LMArena Text: English | 1422 | 1447 | MiMo-V2.5 |
| LMArena Text: non-English | 1405 | 1405 | GPT-5.2 |
| LMArena Text: Chinese | 1447 | 1469 | MiMo-V2.5 |
| LMArena Text: German | 1444 | 1421 | GPT-5.2 |
| LMArena Text: Japanese | 1420 | 1306 | GPT-5.2 |
| LMArena Text: Korean | 1374 | 1361 | GPT-5.2 |
| LMArena Text: French | 1454 | 1448 | GPT-5.2 |
| LMArena Text: Spanish | 1413 | 1414 | MiMo-V2.5 |
| LMArena Text: Russian | 1415 | 1396 | GPT-5.2 |
| LMArena Text: Polish | 1426 | 1413 | GPT-5.2 |
| LMArena Text: multi-turn | 1419 | 1445 | MiMo-V2.5 |
| LMArena Text: longer queries | 1413 | 1445 | MiMo-V2.5 |
| LMArena Text: writing and language | 1392 | 1409 | MiMo-V2.5 |
| LMArena Text: entertainment and media | 1378 | 1399 | MiMo-V2.5 |
| LMArena Vision: English | 1243 | 1259 | MiMo-V2.5 |
| LMArena Vision: Chinese | 1305 | 1326 | MiMo-V2.5 |
| LMArena Vision: reading text | 1257 | 1256 | GPT-5.2 |
| LMArena Vision: humor | 1227 | 1226 | GPT-5.2 |
| LMArena Vision: captioning | 1267 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: recognizing things | 1232 | 1189 | GPT-5.2 |
| LMArena Vision: creative writing | 1225 | 1230 | MiMo-V2.5 |
| LMArena Document | 1405 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2 | 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-5.2 | Xiaomi MiMo-V2.5 |
|---|---|---|
| Maker | OpenAI | Xiaomi |
| Weights | No public weights listed | Open weights |
| Released | December 10, 2025 | April 22, 2026 |
| Context window | 400K | 1.05M |
| Input $/Mtok | $1.75 | $0.168 |
| Output $/Mtok | $14.00 | $0.336 |
| Coding index | 55.9 | 50.0 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $1.91 | $0.01 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2 better than MiMo-V2.5 for coding?
Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 50.0 for MiMo-V2.5. Pick MiMo-V2.5 for output tokens 41.7x cheaper ($0.336 vs $14.00 per million) and a lower cost per solved task ($0.01 against $1.91).
Which is cheaper, GPT-5.2 or MiMo-V2.5?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; MiMo-V2.5 costs $0.168 and $0.336. Per solved SWE-bench Verified task, GPT-5.2 costs $1.91 and MiMo-V2.5 $0.01.
Which has the bigger context window, GPT-5.2 or MiMo-V2.5?
MiMo-V2.5, with 1.05M tokens against 400K.
How many benchmarks is the GPT-5.2 vs MiMo-V2.5 comparison based on?
69 benchmarks have a result for both models as of October 22, 2026. GPT-5.2's coding index rests on 3 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.