GPT-4 vs Kimi K2 0905
Updated October 21, 2026. 4 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
GPT-4 has the edge where what matters is AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
- Shared results
- 4
- GPT-4 only
- 41
- Kimi K2 0905 only
- 12
- Like-for-like categories
- 4 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Kimi K2 0905
Kimi K2 0905 leads, 15.3 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Kimi K2 0905 has a Design Arena: websites result, 1089.
Directional only
Long documents
Listed context window
Kimi K2 0905
Kimi K2 0905 takes 262K tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2 0905
GPT-4 $0.060, Kimi K2 0905 $0.0019 per turn.
List prices
At a glance
- Coding index
- GPT-4 not benchmarked, Kimi K2 0905 not benchmarked.
- Widest category
- Reasoning, 41.8 points apart on average over 1 shared benchmark.
- Widest single gap
- GPQA Diamond (Artificial Analysis run): GPT-4 34.9% against Kimi K2 0905 76.7%, 41.8 points apart on a 0 to 100 scale.
- Output price
- GPT-4 $60.00 against Kimi K2 0905 $2.50 per million output tokens, 24.0x apart.
- Context window
- GPT-4 takes 8K tokens, Kimi K2 0905 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-4 | Bars | Kimi K2 0905 | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 1 | ||
| Knowledge | 0 | 1 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 4 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index10 boards, none shared
| Benchmark | GPT-4 | Kimi K2 0905 | Leader |
|---|---|---|---|
| SWE-bench Verified | 22.4% | Not measured | Only GPT-4 measured |
| SWE-bench Lite | 39.7% | Not measured | Only GPT-4 measured |
| SWE-bench (full test set) | 12.5% | Not measured | Only GPT-4 measured |
| AA Coding Index | 13.1 | Not measured | Only GPT-4 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 61.0% | Only Kimi K2 0905 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 23.5% | Only Kimi K2 0905 measured |
| WeirdML | Not measured | 36.7% | Only Kimi K2 0905 measured |
| ALE-Bench | Not measured | 267.1 | Only Kimi K2 0905 measured |
| LMArena Text: coding | 1209 | Not measured | Only GPT-4 measured |
| LMArena Text: software and IT | 1195 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | Kimi K2 0905 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 15.3 | Kimi K2 0905 |
| Epoch Capabilities Index | 125.7 | Not measured | Only GPT-4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | GPT-4 | Kimi K2 0905 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 73.4% | Only Kimi K2 0905 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | Kimi K2 0905 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 34.9% | 76.7% | Kimi K2 0905 |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 6.4% | Only Kimi K2 0905 measured |
| BIG-Bench Hard | 75.1% | Not measured | Only GPT-4 measured |
| LMArena Text: hard prompts | 1200 | Not measured | Only GPT-4 measured |
| LMArena Text: expert | 1149 | Not measured | Only GPT-4 measured |
| LMArena Text: hard prompts in English | 1209 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | GPT-4 | Kimi K2 0905 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 57.3 | Only Kimi K2 0905 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 57.3% | Only Kimi K2 0905 measured |
| GSM8K | 92.0% | Not measured | Only GPT-4 measured |
| LMArena Text: math | 1230 | Not measured | Only GPT-4 measured |
| LMArena Text: mathematical work | 1228 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | Kimi K2 0905 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 56.2% | 81.9% | Kimi K2 0905 |
| MMLU | 86.4% | Not measured | Only GPT-4 measured |
| AI2 Reasoning Challenge | 96.3% | Not measured | Only GPT-4 measured |
| LMArena Text: science | 1177 | Not measured | Only GPT-4 measured |
| LMArena Text: medicine and healthcare | 1145 | Not measured | Only GPT-4 measured |
| LMArena Text: legal and government | 1191 | Not measured | Only GPT-4 measured |
| LMArena Text: business and finance | 1145 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | GPT-4 | Kimi K2 0905 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1089 | Only Kimi K2 0905 measured |
| Design Arena: all code categories | Not measured | 1098 | Only Kimi K2 0905 measured |
| Neither model has a result on the other 7 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | Kimi K2 0905 | Leader |
|---|---|---|---|
| IFBench | 33.2% | 41.7% | Kimi K2 0905 |
| Long context reasoning (AA-LCR) | Not measured | 53.0% | Only Kimi K2 0905 measured |
| DTBench | 62.7% | Not measured | Only GPT-4 measured |
| LMCA | 17.1% | Not measured | Only GPT-4 measured |
| Fiction.LiveBench | Not measured | 66.7% | Only Kimi K2 0905 measured |
| HellaSwag | 95.3% | Not measured | Only GPT-4 measured |
| WinoGrande | 87.5% | Not measured | Only GPT-4 measured |
| LMArena Text | 1206 | Not measured | Only GPT-4 measured |
| LMArena Text: instruction following | 1201 | Not measured | Only GPT-4 measured |
| LMArena Text: creative writing | 1191 | Not measured | Only GPT-4 measured |
| LMArena Text: English | 1220 | Not measured | Only GPT-4 measured |
| LMArena Text: non-English | 1194 | Not measured | Only GPT-4 measured |
| LMArena Text: Chinese | 1184 | Not measured | Only GPT-4 measured |
| LMArena Text: German | 1198 | Not measured | Only GPT-4 measured |
| LMArena Text: Japanese | 1137 | Not measured | Only GPT-4 measured |
| LMArena Text: Korean | 1087 | Not measured | Only GPT-4 measured |
| LMArena Text: French | 1220 | Not measured | Only GPT-4 measured |
| LMArena Text: Spanish | 1197 | Not measured | Only GPT-4 measured |
| LMArena Text: Russian | 1195 | Not measured | Only GPT-4 measured |
| LMArena Text: Polish | 1265 | Not measured | Only GPT-4 measured |
| LMArena Text: multi-turn | 1206 | Not measured | Only GPT-4 measured |
| LMArena Text: longer queries | 1190 | Not measured | Only GPT-4 measured |
| LMArena Text: writing and language | 1219 | Not measured | Only GPT-4 measured |
| LMArena Text: entertainment and media | 1184 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | Kimi K2 0905 | 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 0905 costs less
Repository review
50K input + 3K output tokens
Kimi K2 0905 costs less
Agent loop
200K input + 10K output tokens
Kimi K2 0905 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-4 | MoonshotAI Kimi K2 0905 |
|---|---|---|
| Maker | OpenAI | Moonshot AI |
| Weights | No public weights listed | Open weights |
| Released | May 28, 2023 | September 4, 2025 |
| Context window | 8K | 262K |
| Input $/Mtok | $30.00 | $0.60 |
| Output $/Mtok | $60.00 | $2.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4 better than Kimi K2 0905 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. GPT-4 has the edge where what matters is AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
Which is cheaper, GPT-4 or Kimi K2 0905?
GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; Kimi K2 0905 costs $0.60 and $2.50. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-4 or Kimi K2 0905?
Kimi K2 0905, with 262K tokens against 8K.
How many benchmarks is the GPT-4 vs Kimi K2 0905 comparison based on?
4 benchmarks have a result for both models as of October 21, 2026. GPT-4's coding index rests on 0 independent benchmarks and Kimi K2 0905's on 0. Where only one model has a result, the page says so instead of naming a winner.