gpt-oss-20b vs Kimi K2 0711
Updated October 21, 2026. 26 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-oss-20b has the edge where output tokens cost 15.3x less, and where what matters is Terminal-Bench Hard (Artificial Analysis run) or Terminal-Bench, where it leads.
- Shared results
- 26
- gpt-oss-20b only
- 34
- Kimi K2 0711 only
- 10
- Like-for-like categories
- 8 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 0711
Kimi K2 0711 leads, 12.7 against 10.0.
Same board, both measured
Reasoning
GPQA Diamond
Kimi K2 0711
Kimi K2 0711 leads, 71.5% against 68.9%.
Same board, both measured
Math
AIME
gpt-oss-20b
gpt-oss-20b leads, 86.0% against 62.7%.
Same board, both measured
Knowledge
MMLU Pro
Kimi K2 0711
Kimi K2 0711 leads, 79.4% against 71.6%.
Same board, both measured
Web design
Design Arena: websites
Kimi K2 0711
Kimi K2 0711 leads, 1050 against 853.
Same board, both measured
Long documents
Listed context window
No call
Both take 131K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-20b
gpt-oss-20b $0.0001, Kimi K2 0711 $0.0017 per turn.
List prices
At a glance
- Coding index
- gpt-oss-20b not benchmarked, Kimi K2 0711 not benchmarked.
- Widest category
- General, 21.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- AIME 2025 (Artificial Analysis run): gpt-oss-20b 89.3% against Kimi K2 0711 57.0%, 32.3 points apart on a 0 to 100 scale.
- Output price
- gpt-oss-20b $0.15 against Kimi K2 0711 $2.30 per million output tokens, 15.3x apart.
- Context window
- Both take 131K tokens.
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-oss-20b | Bars | Kimi K2 0711 | Ties |
|---|---|---|---|---|
| Coding | 3 | 2 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 1 | 2 | ||
| Math | 3 | 1 | 1 tie | |
| Knowledge | 1 | 5 | ||
| Web design | 0 | 2 | ||
| General | 1 | 1 | ||
| All shared boards | 9 | 16 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index32
| Benchmark | gpt-oss-20b | Kimi K2 0711 | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 59.1% | Only Kimi K2 0711 measured |
| SWE-bench Verified | Not measured | 71.2% | Only Kimi K2 0711 measured |
| LiveCodeBench (Vals AI) | 80.4% | 70.5% | gpt-oss-20b |
| LiveCodeBench (Artificial Analysis run) | 77.7% | 55.6% | gpt-oss-20b |
| SciCode | 38.9% | Not measured | Only gpt-oss-20b measured |
| Terminal-Bench Hard (Artificial Analysis run) | 10.6% | 15.9% | Kimi K2 0711 |
| Terminal-Bench | 3.4% | 27.8% | Kimi K2 0711 |
| GSO-Bench | Not measured | 4.9% | Only Kimi K2 0711 measured |
| WeirdML | 40.9% | 39.4% | gpt-oss-20b |
| ALE-Bench | 566.0 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: coding | 1307 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: software and IT | 1311 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | gpt-oss-20b | Kimi K2 0711 | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.0 | 12.7 | Kimi K2 0711 |
| Epoch Capabilities Index | 137.7 | 140.0 | Kimi K2 0711 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | gpt-oss-20b | Kimi K2 0711 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 60.2% | 61.1% | Kimi K2 0711 |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | gpt-oss-20b | Kimi K2 0711 | Leader |
|---|---|---|---|
| GPQA Diamond | 68.9% | 71.5% | Kimi K2 0711 |
| GPQA Diamond (Artificial Analysis run) | 68.8% | 76.6% | Kimi K2 0711 |
| Humanity's Last Exam (Artificial Analysis run) | 11.0% | 7.4% | gpt-oss-20b |
| GPQA Diamond (Epoch AI run) | 60.8% | Not measured | Only gpt-oss-20b measured |
| SimpleBench | Not measured | 26.3% | Only Kimi K2 0711 measured |
| LMArena Text: hard prompts | 1274 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: expert | 1258 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: hard prompts in English | 1292 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 13 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | gpt-oss-20b | Kimi K2 0711 | Leader |
|---|---|---|---|
| AIME | 86.0% | 62.7% | gpt-oss-20b |
| MATH 500 (Vals AI) | 94.2% | 94.2% | Tie |
| MGSM (Vals AI) | 89.0% | 91.0% | Kimi K2 0711 |
| AA Math Index | 89.3 | 57.0 | gpt-oss-20b |
| AIME 2025 (Artificial Analysis run) | 89.3% | 57.0% | gpt-oss-20b |
| OTIS Mock AIME | 65.3% | Not measured | Only gpt-oss-20b measured |
| LMArena Text: math | 1317 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: mathematical work | 1305 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | gpt-oss-20b | Kimi K2 0711 | Leader |
|---|---|---|---|
| MMLU Pro | 71.6% | 79.4% | Kimi K2 0711 |
| LegalBench (Vals AI) | 70.8% | 81.5% | Kimi K2 0711 |
| CaseLaw (Vals AI) | 43.8% | Not measured | Only gpt-oss-20b measured |
| CorpFin (Vals AI) | 53.1% | 50.4% | gpt-oss-20b |
| TaxEval (Vals AI) | 63.7% | 70.2% | Kimi K2 0711 |
| MedQA (Vals AI) | 82.9% | 84.0% | Kimi K2 0711 |
| MMLU Pro (Artificial Analysis run) | 74.8% | 82.4% | Kimi K2 0711 |
| LMArena Text: science | 1296 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: medicine and healthcare | 1310 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: legal and government | 1280 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: business and finance | 1284 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | gpt-oss-20b | Kimi K2 0711 | Leader |
|---|---|---|---|
| Design Arena: websites | 853 | 1050 | Kimi K2 0711 |
| Design Arena: UI components | Not measured | 1030 | Only Kimi K2 0711 measured |
| Design Arena: game dev | Not measured | 974 | Only Kimi K2 0711 measured |
| Design Arena: data viz | 933 | 1018 | Kimi K2 0711 |
| Design Arena: all code categories | Not measured | 1033 | Only Kimi K2 0711 measured |
| Neither model has a result on the other 4 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | gpt-oss-20b | Kimi K2 0711 | Leader |
|---|---|---|---|
| IFBench | 65.1% | 41.5% | gpt-oss-20b |
| Long context reasoning (AA-LCR) | 34.7% | 53.0% | Kimi K2 0711 |
| DTBench | 68.0% | Not measured | Only gpt-oss-20b measured |
| LMCA | 14.5% | Not measured | Only gpt-oss-20b measured |
| Fiction.LiveBench | Not measured | 61.1% | Only Kimi K2 0711 measured |
| Creative writing (Lech Mazur) | Not measured | 85.6% | Only Kimi K2 0711 measured |
| CL-bench | Not measured | 11.9% | Only Kimi K2 0711 measured |
| LMArena Text | 1288 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: instruction following | 1236 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: creative writing | 1201 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: English | 1303 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: non-English | 1269 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Chinese | 1315 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: German | 1255 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Japanese | 1244 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Korean | 1236 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Spanish | 1267 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Russian | 1278 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: Polish | 1252 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: multi-turn | 1268 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: longer queries | 1250 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: writing and language | 1238 | Not measured | Only gpt-oss-20b measured |
| LMArena Text: entertainment and media | 1216 | Not measured | Only gpt-oss-20b measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | gpt-oss-20b | Kimi K2 0711 | 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
gpt-oss-20b costs less
Repository review
50K input + 3K output tokens
gpt-oss-20b costs less
Agent loop
200K input + 10K output tokens
gpt-oss-20b 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-oss-20b | MoonshotAI Kimi K2 0711 |
|---|---|---|
| Maker | OpenAI | Moonshot AI |
| Weights | Open weights | Open weights |
| Released | August 5, 2025 | July 11, 2025 |
| Context window | 131K | 131K |
| Input $/Mtok | $0.03 | $0.57 |
| Output $/Mtok | $0.15 | $2.30 |
| 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-oss-20b better than Kimi K2 0711 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. gpt-oss-20b has the edge where output tokens cost 15.3x less, and where what matters is Terminal-Bench Hard (Artificial Analysis run) or Terminal-Bench, where it leads.
Which is cheaper, gpt-oss-20b or Kimi K2 0711?
gpt-oss-20b costs $0.03 per million input tokens and $0.15 per million output tokens; Kimi K2 0711 costs $0.57 and $2.30. Cost per solved task is known for neither of them.
Which has the bigger context window, gpt-oss-20b or Kimi K2 0711?
Neither: both take 131K tokens.
How many benchmarks is the gpt-oss-20b vs Kimi K2 0711 comparison based on?
26 benchmarks have a result for both models as of October 21, 2026. gpt-oss-20b's coding index rests on 0 independent benchmarks and Kimi K2 0711's on 0. Where only one model has a result, the page says so instead of naming a winner.