Kimi K2-Thinking-0905 vs Qwen3-235B-A22B-Thinking-2507: Specs & Benchmark Comparison
| Characteristic | Kimi K2-Thinking-0905 | Qwen3-235B-A22B-Thinking-2507 |
|---|---|---|
| Company | Moonshot AI | Alibaba |
| Release Date | September 4, 2025 | July 24, 2025 |
| Parameters | 1.0T | 235B |
| Multimodal | No | No |
| Context (input) | 262K | 256K |
| Context (output) | 66K | 131K |
| Input Price / 1M | $0.60 | $0.30 |
| Output Price / 1M | $2.40 | $3.00 |
| Average Score | 0.9 | 0.9 |
| Benchmarks | ||
| AIME 2025 | 1.0 | 0.9 |
| MMLU-Redux | 0.9 | 0.9 |
Visual Benchmark Comparison
Kimi K2-Thinking-0905
Qwen3-235B-A22B-Thinking-2507
AIME 20251.0 vs 0.9
1.0
0.9
MMLU-Redux0.9 vs 0.9
0.9
0.9
Verdict
Kimi K2-Thinking-0905 leads in 3 out of 4 comparison categories.
Overall Performance
Both models show comparable average scores: Kimi K2-Thinking-0905 — 0.9, Qwen3-235B-A22B-Thinking-2507 — 0.9.
API Cost
Kimi K2-Thinking-0905 is 1.1x cheaper: input $0.60/1M vs $0.30/1M tokens.
Context Window
Kimi K2-Thinking-0905 supports a larger context: 262K vs 256K tokens.
Recency
Kimi K2-Thinking-0905 is newer: released 9/4/2025 vs 7/24/2025.
More About These Models
Related Comparisons
The Kimi K2-Thinking-0905 and Qwen3-235B-A22B-Thinking-2507 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Kimi K2-Thinking-0905 or Qwen3-235B-A22B-Thinking-2507 page. See also the complete list of AI model comparisons.