GPT-5.2 vs Kimi K2 Thinking
GPT-5.2 leads Kimi K2 Thinking on the Artificial Analysis Intelligence Index, 30.4 to 22.0, and Kimi K2 Thinking costs 5.6x less per output token ($2.50 vs $14.00 per million). Updated October 22, 2026; 30 benchmarks have a result for both.
GPT-5.2 or Kimi K2 Thinking: which to pick
Only GPT-5.2 has a coding score, 55.9 on the Vibe Coding Index; Kimi K2 Thinking has none, so the two cannot be ranked on coding.
Pick Kimi K2 Thinking for output tokens 5.6x cheaper ($2.50 vs $14.00 per million) and a lower cost per solved task ($0.61 against $1.91).
- Shared results
- 30
- GPT-5.2 only
- 84
- Kimi K2 Thinking only
- 0
- 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
No call
Only GPT-5.2 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.2
GPT-5.2 leads, 30.4 against 22.0.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.2
GPT-5.2 leads, 91.7% against 78.5%.
Same board, both measured
Math
AIME
GPT-5.2
GPT-5.2 leads, 96.9% against 85.4%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5.2
GPT-5.2 leads, 86.2% against 81.1%.
Same board, both measured
Web design
Design Arena: websites
GPT-5.2
GPT-5.2 leads, 1195 against 1113.
Same board, both measured
Long documents
Listed context window
GPT-5.2
GPT-5.2 takes 400K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2 Thinking
GPT-5.2 $0.0088, Kimi K2 Thinking $0.0019 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2 Thinking
GPT-5.2 $1.91, Kimi K2 Thinking $0.61.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.2 55.9 from 3 benchmarks, Kimi K2 Thinking not benchmarked.
- Widest category
- Coding, 18.6 points apart on average over 8 shared benchmarks.
- Widest single gap
- WeirdML: GPT-5.2 72.2% against Kimi K2 Thinking 42.8%, 29.4 points apart on a 0 to 100 scale.
- Output price
- GPT-5.2 $14.00 against Kimi K2 Thinking $2.50 per million output tokens, 5.6x apart.
- Context window
- GPT-5.2 takes 400K tokens, Kimi K2 Thinking 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.
| Category | GPT-5.2 | Bars | Kimi K2 Thinking | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 1 | ||
| Reasoning | 3 | 0 | ||
| Math | 4 | 0 | ||
| Knowledge | 7 | 0 | ||
| Web design | 1 | 0 | ||
| General | 3 | 0 | ||
| All shared boards | 29 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
| Benchmark | GPT-5.2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| SWE-bench Verified | 72.8% | 63.4% | GPT-5.2 |
| SWE-bench Multilingual | 66.7% | Not measured | Only GPT-5.2 measured |
| LMArena WebDev | 1417 | Not measured | Only GPT-5.2 measured |
| LiveCodeBench (Vals AI) | 85.4% | 63.1% | GPT-5.2 |
| SWE-bench Verified (Vals AI) | 75.8% | 60.2% | GPT-5.2 |
| Vibe Code Bench (Vals AI) | 53.5% | Not measured | Only GPT-5.2 measured |
| LiveCodeBench (Artificial Analysis run) | 89.4% | 85.3% | GPT-5.2 |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 31.1% | GPT-5.2 |
| Terminal-Bench | 64.9% | 35.7% | GPT-5.2 |
| GSO-Bench | 27.5% | Not measured | Only GPT-5.2 measured |
| WeirdML | 72.2% | 42.8% | GPT-5.2 |
| ALE-Bench | 1293.5 | 597.5 | GPT-5.2 |
| LMArena Text: coding | 1442 | Not measured | Only GPT-5.2 measured |
| LMArena Text: software and IT | 1434 | Not measured | Only GPT-5.2 measured |
| LMArena WebDev: HTML | 1427 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 22.0 | GPT-5.2 |
| Epoch Capabilities Index | 153.7 | 145.8 | GPT-5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-5.2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| 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 | 1060 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Godot games | 1142 | Not measured | Only GPT-5.2 measured |
| τ²-Bench Telecom | 84.8% | 93.0% | Kimi K2 Thinking |
| METR time horizons | 75.3% | 59.2% | GPT-5.2 |
| 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 29 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-5.2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| GPQA Diamond | 91.7% | 78.5% | GPT-5.2 |
| MMMU Pro (Vals AI) | 86.7% | Not measured | Only GPT-5.2 measured |
| GPQA Diamond (Artificial Analysis run) | 90.3% | 83.8% | GPT-5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 37.7% | 23.8% | 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 | Not measured | Only GPT-5.2 measured |
| LMArena Text: expert | 1445 | Not measured | Only GPT-5.2 measured |
| LMArena Text: hard prompts in English | 1431 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: diagrams | 1265 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: homework | 1276 | Not measured | Only GPT-5.2 measured |
| 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 index40
| Benchmark | GPT-5.2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AIME | 96.9% | 85.4% | GPT-5.2 |
| MGSM (Vals AI) | 94.0% | 90.2% | GPT-5.2 |
| AA Math Index | 99.0 | 94.7 | GPT-5.2 |
| AIME 2025 (Artificial Analysis run) | 99.0% | 94.7% | GPT-5.2 |
| 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% | Not measured | Only GPT-5.2 measured |
| LMArena Text: math | 1440 | Not measured | Only GPT-5.2 measured |
| LMArena Text: mathematical work | 1442 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | GPT-5.2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 81.1% | GPT-5.2 |
| LegalBench (Vals AI) | 82.8% | 80.2% | GPT-5.2 |
| CaseLaw (Vals AI) | 66.0% | 65.7% | GPT-5.2 |
| CorpFin (Vals AI) | 65.9% | 60.6% | GPT-5.2 |
| TaxEval (Vals AI) | 75.8% | 71.7% | GPT-5.2 |
| MortgageTax (Vals AI) | 67.1% | Not measured | Only GPT-5.2 measured |
| MedQA (Vals AI) | 94.1% | 92.6% | GPT-5.2 |
| MedCode (Vals AI) | 49.8% | Not measured | Only GPT-5.2 measured |
| MMLU Pro (Artificial Analysis run) | 87.4% | 84.8% | GPT-5.2 |
| SimpleQA Verified | 37.1% | Not measured | Only GPT-5.2 measured |
| LMArena Text: science | 1425 | Not measured | Only GPT-5.2 measured |
| LMArena Text: medicine and healthcare | 1425 | Not measured | Only GPT-5.2 measured |
| LMArena Text: legal and government | 1427 | Not measured | Only GPT-5.2 measured |
| LMArena Text: business and finance | 1414 | Not measured | Only GPT-5.2 measured |
| 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 index10
| Benchmark | GPT-5.2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| Design Arena: websites | 1195 | 1113 | GPT-5.2 |
| Design Arena: UI components | 1188 | Not measured | Only GPT-5.2 measured |
| Design Arena: game dev | 1195 | Not measured | Only GPT-5.2 measured |
| Design Arena: data viz | 1202 | Not measured | Only GPT-5.2 measured |
| Design Arena: 3D | 1079 | Not measured | Only GPT-5.2 measured |
| Design Arena: all code categories | 1170 | Not measured | Only GPT-5.2 measured |
| Design Arena: SVG | 1139 | Not measured | Only GPT-5.2 measured |
| Design Arena: ASCII art | 1152 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-5.2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 49.3% | Not measured | Only GPT-5.2 measured |
| MedScribe (Vals AI) | 84.4% | Not measured | Only GPT-5.2 measured |
| IFBench | 75.4% | 68.1% | GPT-5.2 |
| Long context reasoning (AA-LCR) | 82.7% | 72.0% | 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% | 17.6% | GPT-5.2 |
| Furniture assembly | 38.3% | Not measured | Only GPT-5.2 measured |
| LMArena Text | 1416 | Not measured | Only GPT-5.2 measured |
| LMArena Text: instruction following | 1409 | Not measured | Only GPT-5.2 measured |
| LMArena Text: creative writing | 1376 | Not measured | Only GPT-5.2 measured |
| LMArena Vision | 1246 | Not measured | Only GPT-5.2 measured |
| LMArena Text: English | 1422 | Not measured | Only GPT-5.2 measured |
| LMArena Text: non-English | 1405 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Chinese | 1447 | Not measured | Only GPT-5.2 measured |
| LMArena Text: German | 1444 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Japanese | 1420 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Korean | 1374 | Not measured | Only GPT-5.2 measured |
| LMArena Text: French | 1454 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Spanish | 1413 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Russian | 1415 | Not measured | Only GPT-5.2 measured |
| LMArena Text: Polish | 1426 | Not measured | Only GPT-5.2 measured |
| LMArena Text: multi-turn | 1419 | Not measured | Only GPT-5.2 measured |
| LMArena Text: longer queries | 1413 | Not measured | Only GPT-5.2 measured |
| LMArena Text: writing and language | 1392 | Not measured | Only GPT-5.2 measured |
| LMArena Text: entertainment and media | 1378 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: English | 1243 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: Chinese | 1305 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: reading text | 1257 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: humor | 1227 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: captioning | 1267 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: recognizing things | 1232 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: creative writing | 1225 | Not measured | Only GPT-5.2 measured |
| LMArena Document | 1405 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2 | Kimi K2 Thinking | 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
Kimi K2 Thinking costs less
Repository review
50K input + 3K output tokens
Kimi K2 Thinking costs less
Agent loop
200K input + 10K output tokens
Kimi K2 Thinking 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 | MoonshotAI Kimi K2 Thinking |
|---|---|---|
| Maker | OpenAI | Moonshot AI |
| Weights | No public weights listed | Open weights |
| Released | December 10, 2025 | November 6, 2025 |
| Context window | 400K | 262K |
| Input $/Mtok | $1.75 | $0.60 |
| Output $/Mtok | $14.00 | $2.50 |
| Coding index | 55.9 | Not benchmarked |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $1.91 | $0.61 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2 better than Kimi K2 Thinking for coding?
Only GPT-5.2 has a coding score, 55.9 on the Vibe Coding Index; Kimi K2 Thinking has none, so the two cannot be ranked on coding. Pick Kimi K2 Thinking for output tokens 5.6x cheaper ($2.50 vs $14.00 per million) and a lower cost per solved task ($0.61 against $1.91).
Which is cheaper, GPT-5.2 or Kimi K2 Thinking?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; Kimi K2 Thinking costs $0.60 and $2.50. Per solved SWE-bench Verified task, GPT-5.2 costs $1.91 and Kimi K2 Thinking $0.61.
Which has the bigger context window, GPT-5.2 or Kimi K2 Thinking?
GPT-5.2, with 400K tokens against 262K.
How many benchmarks is the GPT-5.2 vs Kimi K2 Thinking comparison based on?
30 benchmarks have a result for both models as of October 22, 2026. GPT-5.2's coding index rests on 3 independent benchmarks and Kimi K2 Thinking's on 1. Where only one model has a result, the page says so instead of naming a winner.