GPT-5.4 Mini vs Kimi K2 Thinking
GPT-5.4 Mini leads Kimi K2 Thinking on the Artificial Analysis Intelligence Index, 24.1 to 22.0, and Kimi K2 Thinking costs 1.8x less per output token ($2.50 vs $4.50 per million). Updated October 22, 2026; 18 benchmarks have a result for both.
GPT-5.4 Mini or Kimi K2 Thinking: which to pick
Only GPT-5.4 Mini has a coding score, 35.8 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 1.8x cheaper ($2.50 vs $4.50 per million) and a lower cost per solved task ($0.61 against $0.70).
- Shared results
- 18
- GPT-5.4 Mini only
- 71
- Kimi K2 Thinking only
- 12
- Like-for-like categories
- 7 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-5.4 Mini has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.4 Mini
GPT-5.4 Mini leads, 24.1 against 22.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GPT-5.4 Mini has a AA Agentic Index result, 17.9.
Directional only
Reasoning
GPQA Diamond
GPT-5.4 Mini
GPT-5.4 Mini leads, 83.1% against 78.5%.
Same board, both measured
Math
AIME
GPT-5.4 Mini
GPT-5.4 Mini leads, 95.6% against 85.4%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5.4 Mini
GPT-5.4 Mini leads, 84.5% against 81.1%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Kimi K2 Thinking has a Design Arena: websites result, 1113.
Directional only
Long documents
Listed context window
GPT-5.4 Mini
GPT-5.4 Mini takes 400K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2 Thinking
GPT-5.4 Mini $0.0030, Kimi K2 Thinking $0.0019 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2 Thinking
GPT-5.4 Mini $0.70, Kimi K2 Thinking $0.61.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.4 Mini 35.8 from 5 benchmarks, Kimi K2 Thinking not benchmarked.
- Widest category
- Coding, 17.9 points apart on average over 5 shared benchmarks.
- Widest single gap
- Terminal-Bench Hard (Artificial Analysis run): GPT-5.4 Mini 52.3% against Kimi K2 Thinking 31.1%, 21.2 points apart on a 0 to 100 scale.
- Output price
- GPT-5.4 Mini $4.50 against Kimi K2 Thinking $2.50 per million output tokens, 1.8x apart.
- Context window
- GPT-5.4 Mini 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-5.4 Mini | Bars | Kimi K2 Thinking | Ties |
|---|---|---|---|---|
| Coding | 5 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 3 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 2 | 2 | ||
| General | 2 | 0 | ||
| All shared boards | 15 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
| Benchmark | GPT-5.4 Mini | Kimi K2 Thinking | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 63.4% | Only Kimi K2 Thinking measured |
| LMArena WebDev | 1397 | Not measured | Only GPT-5.4 Mini measured |
| AA Coding Index | 56.1 | Not measured | Only GPT-5.4 Mini measured |
| LiveCodeBench (Vals AI) | 81.5% | 63.1% | GPT-5.4 Mini |
| SWE-bench Verified (Vals AI) | 73.0% | 60.2% | GPT-5.4 Mini |
| Terminal-Bench 4 (Vals AI) | 2.5% | Not measured | Only GPT-5.4 Mini measured |
| Vibe Code Bench (Vals AI) | 48.0% | Not measured | Only GPT-5.4 Mini measured |
| Code migration (Vals AI) | 12.9% | Not measured | Only GPT-5.4 Mini measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | Not measured | Only GPT-5.4 Mini measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 85.3% | Only Kimi K2 Thinking measured |
| SciCode | 52.1% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 52.3% | 31.1% | GPT-5.4 Mini |
| Terminal-Bench | Not measured | 35.7% | Only Kimi K2 Thinking measured |
| FrontierCode | 27.0% | Not measured | Only GPT-5.4 Mini measured |
| WeirdML | 60.3% | 42.8% | GPT-5.4 Mini |
| ALE-Bench | 1188.6 | 597.5 | GPT-5.4 Mini |
| LMArena Text: coding | 1438 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: software and IT | 1436 | Not measured | Only GPT-5.4 Mini measured |
| LMArena WebDev: React | 1386 | Not measured | Only GPT-5.4 Mini measured |
| LMArena WebDev: HTML | 1419 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.4 Mini | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.1 | 22.0 | GPT-5.4 Mini |
| Epoch Capabilities Index | 148.7 | 145.8 | GPT-5.4 Mini |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5.4 Mini | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Agentic Index | 17.9 | Not measured | Only GPT-5.4 Mini measured |
| Finance Agent (Vals AI) | 45.4% | Not measured | Only GPT-5.4 Mini measured |
| Tax Agent Bench (Vals AI) | 8.8% | Not measured | Only GPT-5.4 Mini measured |
| Legal Research Bench (Vals AI) | 12.5% | Not measured | Only GPT-5.4 Mini measured |
| Excel Modeling Benchmark (Vals AI) | 45.4% | Not measured | Only GPT-5.4 Mini measured |
| τ²-Bench Telecom | 83.3% | 93.0% | Kimi K2 Thinking |
| METR time horizons | Not measured | 59.2% | Only Kimi K2 Thinking measured |
| DeepResearch Bench | 36.3% | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | GPT-5.4 Mini | Kimi K2 Thinking | Leader |
|---|---|---|---|
| GPQA Diamond | 83.1% | 78.5% | GPT-5.4 Mini |
| MMMU Pro (Vals AI) | 79.3% | Not measured | Only GPT-5.4 Mini measured |
| GPQA Diamond (Artificial Analysis run) | 87.5% | 83.8% | GPT-5.4 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 28.1% | 23.8% | GPT-5.4 Mini |
| GPQA Diamond (Epoch AI run) | 86.9% | Not measured | Only GPT-5.4 Mini measured |
| ARC-AGI | 63.7% | Not measured | Only GPT-5.4 Mini measured |
| ARC-AGI-2 | 18.9% | Not measured | Only GPT-5.4 Mini measured |
| Chess puzzles | 23.0% | Not measured | Only GPT-5.4 Mini measured |
| Mystery game puzzles | 11.0% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts | 1424 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: expert | 1435 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: hard prompts in English | 1420 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: diagrams | 1266 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: homework | 1285 | Not measured | Only GPT-5.4 Mini measured |
| Kagi LLM Benchmark | 37.9% | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.4 Mini | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AIME | 95.6% | 85.4% | GPT-5.4 Mini |
| 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 | 88.9% | Not measured | Only GPT-5.4 Mini measured |
| FrontierMath, tiers 1 to 3 | 51.2% | Not measured | Only GPT-5.4 Mini measured |
| FrontierMath, tier 4 | 9.8% | Not measured | Only GPT-5.4 Mini measured |
| ProofBench | 21.0% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: math | 1418 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: mathematical work | 1429 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | GPT-5.4 Mini | Kimi K2 Thinking | Leader |
|---|---|---|---|
| MMLU Pro | 84.5% | 81.1% | GPT-5.4 Mini |
| LegalBench (Vals AI) | Not measured | 80.2% | Only Kimi K2 Thinking measured |
| CaseLaw (Vals AI) | 51.7% | 65.7% | Kimi K2 Thinking |
| CorpFin (Vals AI) | 60.9% | 60.6% | GPT-5.4 Mini |
| TaxEval (Vals AI) | 71.2% | 71.7% | Kimi K2 Thinking |
| MortgageTax (Vals AI) | 63.5% | Not measured | Only GPT-5.4 Mini measured |
| MedQA (Vals AI) | Not measured | 92.6% | Only Kimi K2 Thinking measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 84.8% | Only Kimi K2 Thinking measured |
| SimpleQA Verified | 29.4% | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: science | 1417 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: medicine and healthcare | 1395 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: legal and government | 1414 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: business and finance | 1418 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | GPT-5.4 Mini | Kimi K2 Thinking | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1113 | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.4 Mini | Kimi K2 Thinking | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 50.8% | Not measured | Only GPT-5.4 Mini measured |
| Vals Multimodal Index | 54.2% | Not measured | Only GPT-5.4 Mini measured |
| IFBench | 73.3% | 68.1% | GPT-5.4 Mini |
| Long context reasoning (AA-LCR) | 77.0% | 72.0% | GPT-5.4 Mini |
| DTBench | 80.0% | Not measured | Only GPT-5.4 Mini measured |
| LMCA | 40.8% | Not measured | Only GPT-5.4 Mini measured |
| CL-bench | Not measured | 17.6% | Only Kimi K2 Thinking measured |
| LMArena Text | 1412 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: instruction following | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: creative writing | 1370 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision | 1245 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: English | 1412 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: non-English | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Chinese | 1446 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: German | 1408 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Japanese | 1375 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Korean | 1370 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: French | 1441 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Spanish | 1405 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Russian | 1417 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: Polish | 1415 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: multi-turn | 1429 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: longer queries | 1408 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: writing and language | 1393 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: entertainment and media | 1373 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: English | 1244 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: Chinese | 1286 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: reading text | 1253 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: humor | 1235 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: recognizing things | 1218 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Vision: creative writing | 1222 | Not measured | Only GPT-5.4 Mini measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.4 Mini | 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-5.4 Mini | MoonshotAI Kimi K2 Thinking |
|---|---|---|
| Maker | OpenAI | Moonshot AI |
| Weights | No public weights listed | Open weights |
| Released | March 17, 2026 | November 6, 2025 |
| Context window | 400K | 262K |
| Input $/Mtok | $0.75 | $0.60 |
| Output $/Mtok | $4.50 | $2.50 |
| Coding index | 35.8 | Not benchmarked |
| Independent measurements behind it | 5 | 1 |
| Cost per solved task | $0.70 | $0.61 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.4 Mini better than Kimi K2 Thinking for coding?
Only GPT-5.4 Mini has a coding score, 35.8 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 1.8x cheaper ($2.50 vs $4.50 per million) and a lower cost per solved task ($0.61 against $0.70).
Which is cheaper, GPT-5.4 Mini or Kimi K2 Thinking?
GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; Kimi K2 Thinking costs $0.60 and $2.50. Per solved SWE-bench Verified task, GPT-5.4 Mini costs $0.70 and Kimi K2 Thinking $0.61.
Which has the bigger context window, GPT-5.4 Mini or Kimi K2 Thinking?
GPT-5.4 Mini, with 400K tokens against 262K.
How many benchmarks is the GPT-5.4 Mini vs Kimi K2 Thinking comparison based on?
18 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Mini's coding index rests on 5 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.