Gemini 3.1 Pro Preview vs Kimi K2 Thinking
Gemini 3.1 Pro Preview leads Kimi K2 Thinking on the Artificial Analysis Intelligence Index, 29.7 to 22.0, and Kimi K2 Thinking costs 4.8x less per output token ($2.50 vs $12.00 per million). Updated October 22, 2026; 23 benchmarks have a result for both.
vs boards won of 23 shared
Gemini 3.1 Pro Preview or Kimi K2 Thinking: which to pick
Only Gemini 3.1 Pro Preview has a coding score, 32.3 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 4.8x cheaper ($2.50 vs $12.00 per million) and a lower cost per solved task ($0.61 against $0.99).
Model AGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved taskModel BKimi K2 ThinkingMoonshot AINot benchmarked1 independent benchmark$0.61 per solved task
- Shared results
- 23
- Gemini 3.1 Pro Preview only
- 110
- Kimi K2 Thinking only
- 7
- 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 Gemini 3.1 Pro Preview has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 29.7 against 22.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.1 Pro Preview has a AA Agentic Index result, 8.2.
Directional only
Reasoning
GPQA Diamond
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 78.5%.
Same board, both measured
Math
AIME
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 98.1% against 85.4%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 81.1%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 1234 against 1113.
Same board, both measured
Long documents
Listed context window
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2 Thinking
Gemini 3.1 Pro Preview $0.0080, Kimi K2 Thinking $0.0019 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2 Thinking
Gemini 3.1 Pro Preview $0.99, Kimi K2 Thinking $0.61.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3.1 Pro Preview 32.3 from 4 benchmarks, Kimi K2 Thinking not benchmarked.
- Widest category
- Coding, 26.5 points apart on average over 6 shared benchmarks.
- Widest single gap
- Terminal-Bench: Gemini 3.1 Pro Preview 80.2% against Kimi K2 Thinking 35.7%, 44.5 points apart on a 0 to 100 scale.
- Output price
- Gemini 3.1 Pro Preview $12.00 against Kimi K2 Thinking $2.50 per million output tokens, 4.8x apart.
- Context window
- Gemini 3.1 Pro Preview takes 1.05M 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 | Gemini 3.1 Pro Preview | Bars | Kimi K2 Thinking | Ties |
|---|---|---|---|---|
| Coding | 6 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 3 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 5 | 1 | ||
| Web design | 1 | 0 | ||
| General | 3 | 0 | ||
| All shared boards | 22 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index60
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 63.4% | Only Kimi K2 Thinking measured |
| LMArena WebDev | 1447 | Not measured | Only Gemini 3.1 Pro Preview measured |
| AA Coding Index | 68.8 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LiveCodeBench (Vals AI) | 88.5% | 63.1% | Gemini 3.1 Pro Preview |
| SWE-bench Verified (Vals AI) | 78.8% | 60.2% | Gemini 3.1 Pro Preview |
| Terminal-Bench 4 (Vals AI) | 2.5% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vibe Code Bench (Vals AI) | 32.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Code migration (Vals AI) | 17.3% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| IOI (Vals AI) | 51.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench 2.1 (Vals AI) | 70.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vibe Code Bench 1-100 (Vals AI) | 6.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 85.3% | Only Kimi K2 Thinking measured |
| SciCode | 58.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench Hard (Artificial Analysis run) | 53.8% | 31.1% | Gemini 3.1 Pro Preview |
| Terminal-Bench | 80.2% | 35.7% | Gemini 3.1 Pro Preview |
| GSO-Bench | 22.6% | Not measured | Only Gemini 3.1 Pro Preview measured |
| WeirdML | 72.1% | 42.8% | Gemini 3.1 Pro Preview |
| MirrorCode | 8.9% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ALE-Bench | 1160.6 | 597.5 | Gemini 3.1 Pro Preview |
| LMArena Text: coding | 1484 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: software and IT | 1487 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena WebDev: React | 1438 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena WebDev: HTML | 1490 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena WebDev: from an image | 1481 | Not measured | Only Gemini 3.1 Pro Preview measured |
| SciCode | 14.3% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 13 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.7 | 22.0 | Gemini 3.1 Pro Preview |
| Epoch Capabilities Index | Not measured | 145.8 | Only Kimi K2 Thinking measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Agentic Index | 8.2 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building web apps | 1125 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building full-stack apps | 1068 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building mobile apps | 1093 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building Android apps | 1050 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building Godot games | 1236 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building games | 1114 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: HTML slides | 1103 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: PowerPoint slides | 1043 | Not measured | Only Gemini 3.1 Pro Preview measured |
| SREBench (Vals AI) | 0.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Finance Agent (Vals AI) | 43.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Tax Agent Bench (Vals AI) | 9.3% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Legal Research Bench (Vals AI) | 20.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Excel Modeling Benchmark (Vals AI) | 52.6% | Not measured | Only Gemini 3.1 Pro Preview measured |
| BioMysteryBench (Vals AI) | 60.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench-Science (Vals AI) | 1.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vals Science Index | 27.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| τ²-Bench Telecom | 95.6% | 93.0% | Gemini 3.1 Pro Preview |
| APEX-Agents | 35.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| METR time horizons | 77.0% | 59.2% | Gemini 3.1 Pro Preview |
| BALROG | 57.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| DeepResearch Bench | 47.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| PostTrainBench | 22.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vending-Bench 2 | $911 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 17 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking | Leader |
|---|---|---|---|
| GPQA Diamond | 95.5% | 78.5% | Gemini 3.1 Pro Preview |
| MysteryMechanism (Vals AI) | 20.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MMMU Pro (Vals AI) | 88.2% | Not measured | Only Gemini 3.1 Pro Preview measured |
| GPQA Diamond (Artificial Analysis run) | 94.1% | 83.8% | Gemini 3.1 Pro Preview |
| Humanity's Last Exam (Artificial Analysis run) | 47.0% | 23.8% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Epoch AI run) | 94.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ARC-AGI | 98.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ARC-AGI-2 | 77.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| SimpleBench | 79.6% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Chess puzzles | 51.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Mystery game puzzles | 34.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| EBR-bench | 14.3% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts | 1485 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: expert | 1483 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts in English | 1480 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: diagrams | 1311 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: homework | 1316 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AIME | 98.1% | 85.4% | Gemini 3.1 Pro Preview |
| MGSM (Vals AI) | Not measured | 90.2% | Only Kimi K2 Thinking measured |
| AA Math Index | Not measured | 94.7 | Only Kimi K2 Thinking measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 94.7% | Only Kimi K2 Thinking measured |
| OTIS Mock AIME | 95.6% | Not measured | Only Gemini 3.1 Pro Preview measured |
| FrontierMath, tiers 1 to 3 | 59.6% | Not measured | Only Gemini 3.1 Pro Preview measured |
| FrontierMath, tier 4 | 26.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ProofBench | 26.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: math | 1486 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: mathematical work | 1478 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Gemini 3.1 Pro Preview | Kimi K2 Thinking | Leader |
|---|---|---|---|
| MMLU Pro | 91.0% | 81.1% | Gemini 3.1 Pro Preview |
| LegalBench (Vals AI) | 87.4% | 80.2% | Gemini 3.1 Pro Preview |
| CaseLaw (Vals AI) | 64.8% | 65.7% | Kimi K2 Thinking |
| CorpFin (Vals AI) | 64.5% | 60.6% | Gemini 3.1 Pro Preview |
| TaxEval (Vals AI) | 72.9% | 71.7% | Gemini 3.1 Pro Preview |
| MortgageTax (Vals AI) | 69.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MedQA (Vals AI) | 96.4% | 92.6% | Gemini 3.1 Pro Preview |
| MedCode (Vals AI) | 59.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 84.8% | Only Kimi K2 Thinking measured |
| SimpleQA Verified | 73.5% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: science | 1497 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: medicine and healthcare | 1486 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: legal and government | 1487 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: business and finance | 1459 | Not measured | Only Gemini 3.1 Pro Preview measured |
| FACTS Benchmark Suite | 67.4% | Not measured | Only Gemini 3.1 Pro Preview 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 | Gemini 3.1 Pro Preview | Kimi K2 Thinking | Leader |
|---|---|---|---|
| Design Arena: websites | 1234 | 1113 | Gemini 3.1 Pro Preview |
| Design Arena: UI components | 1224 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: game dev | 1202 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: data viz | 1209 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: 3D | 1234 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: all code categories | 1230 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: SVG | 1284 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: ASCII art | 1270 | Not measured | Only Gemini 3.1 Pro Preview 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 | Gemini 3.1 Pro Preview | Kimi K2 Thinking | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 53.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| SAGE (Vals AI) | 48.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MedScribe (Vals AI) | 76.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vals Multimodal Index | 56.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| IFBench | 77.1% | 68.1% | Gemini 3.1 Pro Preview |
| Long context reasoning (AA-LCR) | 82.0% | 72.0% | Gemini 3.1 Pro Preview |
| DTBench | 97.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMCA | 53.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| CL-bench | 20.8% | 17.6% | Gemini 3.1 Pro Preview |
| Furniture assembly | 26.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ExploitBench | 26.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| CL-bench Life | 16.9% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text | 1480 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: instruction following | 1466 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: creative writing | 1482 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision | 1296 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: English | 1478 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: non-English | 1476 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Chinese | 1527 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: German | 1490 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Japanese | 1491 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Korean | 1455 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: French | 1487 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Spanish | 1481 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Russian | 1497 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Polish | 1498 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: multi-turn | 1487 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: longer queries | 1482 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: writing and language | 1481 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: entertainment and media | 1465 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: English | 1287 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: Chinese | 1364 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: reading text | 1304 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: humor | 1322 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: captioning | 1345 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: recognizing things | 1330 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: creative writing | 1324 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Document | 1444 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 8 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3.1 Pro Preview | 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
Gemini 3.1 Pro Preview$0.0080Fits in one request
Kimi K2 Thinking$0.0019Fits in one request
Kimi K2 Thinking costs less
Repository review
50K input + 3K output tokens
Gemini 3.1 Pro Preview$0.136Fits in one request
Kimi K2 Thinking$0.037Fits in one request
Kimi K2 Thinking costs less
Agent loop
200K input + 10K output tokens
Gemini 3.1 Pro Preview$0.520Fits in one request
Kimi K2 Thinking$0.145Fits in one request
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 | Google Gemini 3.1 Pro Preview | MoonshotAI Kimi K2 Thinking |
|---|---|---|
| Maker | Moonshot AI | |
| Weights | No public weights listed | Open weights |
| Released | February 19, 2026 | November 6, 2025 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $2.00 | $0.60 |
| Output $/Mtok | $12.00 | $2.50 |
| Coding index | 32.3 | Not benchmarked |
| Independent measurements behind it | 4 | 1 |
| Cost per solved task | $0.99 | $0.61 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3.1 Pro Preview better than Kimi K2 Thinking for coding?
Only Gemini 3.1 Pro Preview has a coding score, 32.3 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 4.8x cheaper ($2.50 vs $12.00 per million) and a lower cost per solved task ($0.61 against $0.99).
Which is cheaper, Gemini 3.1 Pro Preview or Kimi K2 Thinking?
Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; Kimi K2 Thinking costs $0.60 and $2.50. Per solved SWE-bench Verified task, Gemini 3.1 Pro Preview costs $0.99 and Kimi K2 Thinking $0.61.
Which has the bigger context window, Gemini 3.1 Pro Preview or Kimi K2 Thinking?
Gemini 3.1 Pro Preview, with 1.05M tokens against 262K.
How many benchmarks is the Gemini 3.1 Pro Preview vs Kimi K2 Thinking comparison based on?
23 benchmarks have a result for both models as of October 22, 2026. Gemini 3.1 Pro Preview's coding index rests on 4 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.