BenchmarksKimiToday
Kimi K2 Thinking Benchmark Update
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 189.535 tok/s | MMLU: 0.848% | HumanEval: 0.853%
View sourceMoonshot AI
Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.
Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.
41.7
Quality Score
---
Arena ELO
Undisclosed
Parameters
256K
Context
Sign in to join the discussion
4.9K
Downloads
0
Likes
May 2026
Released
Benchmarks
19
API
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 189.535 tok/s | MMLU: 0.848% | HumanEval: 0.853%
View sourceQuality: 32.7/100 | Price: $1.075/M tokens | Output: 189.535 tok/s | MMLU: 0.848% | HumanEval: 0.853%
SWE-Bench Verified resolved rate 63.4
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 185.757 tok/s | MMLU: 0.848% | HumanEval: 0.853%
SWE-Bench Verified resolved rate 63.4
View sourceQuality: 32.7/100 | Price: $1.075/M tokens | Output: 170.678 tok/s | MMLU: 0.848% | HumanEval: 0.853%
View sourceQuality: 32.7/100 | Price: $1.075/M tokens | Output: 164.83 tok/s | MMLU: 0.848% | HumanEval: 0.853%
View sourceQuality: 32.7/100 | Price: $1.075/M tokens | Output: 185.757 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 170.678 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 164.83 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 158.551 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 163.38 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 168.194 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 168.458 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 168.793 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 145.244 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 145.78 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 154.548 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 119.775 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 32.7/100 | Price: $1.075/M tokens | Output: 111.508 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 40.9/100 | Price: $1.075/M tokens | Output: 115.861 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 40.9/100 | Price: $1.075/M tokens | Output: 128.038 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 40.9/100 | Price: $1.075/M tokens | Output: 131.129 tok/s | MMLU: 0.848% | HumanEval: 0.853%
Quality: 40.9/100 | Price: $1.075/M tokens | Output: 129.838 tok/s | MMLU: 0.848% | HumanEval: 0.853%
kimi-k2-thinking is now available through Ollama Cloud. 256K context window listed. Kimi K2 Thinking, Moonshot AI's best open-source thinking model.