Compare · ModelsLive · 2 picked · head to head
Kimi K2 Thinking vs gpt-oss-20b (free)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Kimi K2 Thinking wins on 6/6 benchmarks
Kimi K2 Thinking wins 6 of 6 shared benchmarks. Leads in math · knowledge · language.
Category leads
math·Kimi K2 Thinkingknowledge·Kimi K2 Thinkinglanguage·Kimi K2 Thinkingcoding·Kimi K2 Thinking
Hype vs Reality
Attention vs performance
Kimi K2 Thinking
#79 by perf·no signal
gpt-oss-20b (free)
#27 by perf·no signal
Best value
Kimi K2 Thinking
Kimi K2 Thinking
34.4 pts/$
$1.55/M
gpt-oss-20b (free)
—
$0.00/M
Vendor risk
Who is behind the model
moonshotai
private · undisclosed
OpenAI
$840.0B·Tier 1
Head to head
6 benchmarks · 2 models
Kimi K2 Thinkinggpt-oss-20b (free)
OpenCompass · AIME2025
Kimi K2 Thinking leads by +6.2
Kimi K2 Thinking
94.1
gpt-oss-20b (free)
87.9
OpenCompass · GPQA-Diamond
Kimi K2 Thinking leads by +13.8
Kimi K2 Thinking
82.7
gpt-oss-20b (free)
68.9
OpenCompass · HLE
Kimi K2 Thinking leads by +9.7
Kimi K2 Thinking
21.3
gpt-oss-20b (free)
11.6
OpenCompass · IFEval
Kimi K2 Thinking leads by +3.5
Kimi K2 Thinking
92.4
gpt-oss-20b (free)
88.9
OpenCompass · LiveCodeBenchV6
Kimi K2 Thinking leads by +8.7
Kimi K2 Thinking
77.1
gpt-oss-20b (free)
68.4
OpenCompass · MMLU-Pro
Kimi K2 Thinking leads by +11.5
Kimi K2 Thinking
84.3
gpt-oss-20b (free)
72.8
Full benchmark table
| Benchmark | Kimi K2 Thinking | gpt-oss-20b (free) |
|---|---|---|
OpenCompass · AIME2025 | 94.1 | 87.9 |
OpenCompass · GPQA-Diamond | 82.7 | 68.9 |
OpenCompass · HLE | 21.3 | 11.6 |
OpenCompass · IFEval | 92.4 | 88.9 |
OpenCompass · LiveCodeBenchV6 | 77.1 | 68.4 |
OpenCompass · MMLU-Pro | 84.3 | 72.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.60 | $2.50 | 262K tokens (~131 books) | $10.75 | |
| $0.00 | $0.00 | 131K tokens (~66 books) | — |
People also compared