Kimi K2.5 vs o3-pro vs Qwen3.5 397B-A17B
Too close to call on our weighted score (Kimi K2.5 63, Qwen3.5 397B-A17B 62, o3-pro 49). The right pick depends on what you value most.Too close to call on our weighted score (Kimi K2.5 71, Qwen3.5 397B-A17B 70, o3-pro 69). The right pick depends on what you value most.
Moonshot AI
Kimi K2.5
63/100- ECI148.8
- Price$0.60 / $3.00
- Context262K
OpenAI
o3-pro
49/100- ECI147.5
- Price$20.00 / $80.00
- Context200K
Alibaba (Qwen)
Qwen3.5 397B-A17B
62/100- ECI148.0
- Price$0.60 / $3.60
- Context262K
Moonshot AI
Kimi K2.5
71/100- ECI148.8
- Price$0.60 / $3.00
- Context262K
OpenAI
o3-pro
69/100- ECI147.5
- Price$20.00 / $80.00
- Context200K
Alibaba (Qwen)
Qwen3.5 397B-A17B
70/100- ECI148.0
- Price$0.60 / $3.60
- Context262K
Too close to call
It is close. Our weighted score puts them within 1 points (Kimi K2.5 63/100, Qwen3.5 397B-A17B 62/100, o3-pro 49/100), so choose by what matters most for your work: Kimi K2.5 for raw capability. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within a point (Kimi K2.5 71/100, Qwen3.5 397B-A17B 70/100, o3-pro 69/100), so choose by what matters most for your work: Kimi K2.5 for raw capability. The score weighs capability 83%, context window 17%.
- CapabilityKimi K2.5Capabilities Index (ECI): Kimi K2.5 148.8 · Qwen3.5 397B-A17B 148.0 · o3-pro 147.5
- Lowest priceKimi K2.5Kimi K2.5 $1.20 · Qwen3.5 397B-A17B $1.35 · o3-pro $35.00 per 1M tokens (3:1 blend)
- Longest contextKimi K2.5 and Qwen3.5 397B-A17BKimi K2.5 262,144 · Qwen3.5 397B-A17B 262,144 · o3-pro 200,000 tokens
- Widest inputsKimi K2.5 and Qwen3.5 397B-A17BKimi K2.5: Text, Images, Video · o3-pro: Text, Images · Qwen3.5 397B-A17B: Text, Images, Video
- Self-hostingKimi K2.5 and Qwen3.5 397B-A17BPublishes downloadable weights
| Measure | Weight | Kimi K2.5 | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 59% | 77 | 75 | 76 |
| Price | 29% | 44 | 0 | 42 |
| Context window | 12% | 43 | 39 | 43 |
| Overall | 100% | 63/100 | 49/100 | 62/100 |
Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.
| Measure | Weight | Kimi K2.5 | o3-pro | Qwen3.5 397B-A17B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 83% | 77 | 75 | 76 |
| Context window | 17% | 43 | 39 | 43 |
| Overall | 100% | 71/100 | 69/100 | 70/100 |
Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 148.8 (best) | 147.5 | 148.0 |
| ECI rank | #74 of 159 (best) | #80 of 159 | #76 of 159 |
| ECI confidence interval | 147.3–150.3 | 145.7–149.4 | 145.9–150.1 |
| ECI evaluation date | Jan 27, 2026 | Jun 10, 2025 | Feb 13, 2026 |
| Documented capabilities | Earlier Kimi frontier model for long-context agents, coding, and multimodal work | High-effort o3 tier for difficult technical reasoning and careful answers | Large open Qwen multimodal MoE for visual agents and long technical tasks |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | 87.6% (best) | Not published | 86.4%none |
| FrontierMath Tiers 1–3Research-level mathematics | Not published | Not published | 31.2%none |
| OTIS Mock AIME 2024–2025Competition mathematics | 92.2% (best) | Not published | 88.9% |
| SWE-bench VerifiedFixing real GitHub issues | 73.8% | Not published | Not published |
| SimpleQA VerifiedShort factual questions | 34.3% | Not published | Not published |
| Publisher-reported benchmarks | |||
| SWE-Bench VerifiedPublisher-reported result | 70.8resolvedReported result | Not published | 76.4resolvedReported result |
| SWE-Atlas Codebase QnAPublisher-reported result | 13.1scoreReported result | Not published | Not published |
| SWE-Atlas RefactoringPublisher-reported result | 20.95scoreReported result | Not published | Not published |
| SWE-Atlas Test WritingPublisher-reported result | 25.77scoreReported result | Not published | Not published |
| Aider PolyglotPublisher-reported result | Not published | 84.9percent correctReported resultJun 28, 2025 | Not published |
| Price per million tokens | |||
| Input | $0.60 (best) | $20.00 | $0.60 (best) |
| Output | $3.00 (best) | $80.00 | $3.60 |
| Cached input | Not published | Not published | Not published |
| Blended (3:1) | $1.20 (best) | $35.00 | $1.35 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 36 providers | Official OpenAI API | Official Alibaba API |
| Limits | |||
| Context window | 262,144 tokens (best) | 200,000 tokens | 262,144 tokens (best) |
| Max input | Not published | Not published | Not published |
| Max output | 262,144 tokens (best) | 100,000 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | No | Yes |
| Reasoning | Yes | Yeslow · medium · high | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Not published | Yes | Yes |
| File attachments | Yes | Yes | Yes |
| Temperature control | No | No | Yes |
| Reasoning control | always | effort | budget |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | Not published | o3-pro | qwen3.5-397b-a17b |
| API providers | 36 (best) | 10 | 36 (best) |
| Released | Jan 27, 2026 | Jun 10, 2025 | Feb 15, 2026 |
| Knowledge cutoff | Jan 2025 | May 2024 | Not published |
| Publisher documentation | Model weights | Publisher documentation | Publisher documentation · Model weights |
| Source metadata updated | Jan 27, 2026 | Jun 10, 2025 | Feb 15, 2026 |
| Data sources | models.dev · Epoch AI | models.dev · Epoch AI | models.dev · Epoch AI |
| Catalog checked | Nov 22, 2026 | Nov 22, 2026 | Nov 22, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Kimi K2.5$12.00
o3-pro$360.00
Qwen3.5 397B-A17B$13.20
Which should you choose?
Which is better: Kimi K2.5, o3-pro or Qwen3.5 397B-A17B?
It is close. Our weighted score puts them within 1 points (Kimi K2.5 63/100, Qwen3.5 397B-A17B 62/100, o3-pro 49/100), so choose by what matters most for your work: Kimi K2.5 for raw capability. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within a point (Kimi K2.5 71/100, Qwen3.5 397B-A17B 70/100, o3-pro 69/100), so choose by what matters most for your work: Kimi K2.5 for raw capability. The score weighs capability 83%, context window 17%.
Which is cheaper, Kimi K2.5, o3-pro or Qwen3.5 397B-A17B?
Kimi K2.5 is cheaper at $0.60 input / $3.00 output per million tokens (median across 36 API providers). Qwen3.5 397B-A17B costs $0.60 input / $3.60 output per million tokens (official Alibaba API price); o3-pro costs $20.00 input / $80.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $1.20 per million tokens for Kimi K2.5 versus $1.35 for Qwen3.5 397B-A17B (1.1× as much) and $35.00 for o3-pro (29× as much).
Which scores higher on benchmarks?
Kimi K2.5 scores higher on the Capabilities Index (ECI): Kimi K2.5 148.8 (#74 of 159), Qwen3.5 397B-A17B 148.0 (#76 of 159) and o3-pro 147.5 (#80 of 159). The confidence ranges of the top two overlap (147.3–150.3 vs 145.9–150.1), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for o3-pro and Qwen3.5 397B-A17B yet, so there is no like-for-like coding score. On overall capability, Kimi K2.5 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Kimi K2.5 and Qwen3.5 397B-A17B have the largest context windows (262,144 and 262,144 tokens), against 200,000 for o3-pro. Maximum output per response: Kimi K2.5 up to 262,144, o3-pro up to 100,000, Qwen3.5 397B-A17B up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Kimi K2.5 accepts text, images and video; o3-pro accepts text and images; Qwen3.5 397B-A17B accepts text, images and video. Kimi K2.5 handles the widest range of inputs.
Are any of these open source?
Kimi K2.5 and Qwen3.5 397B-A17B publishes its weights and can be self-hosted; o3-pro is proprietary.
Which is newer?
Qwen3.5 397B-A17B is the newest, released Feb 15, 2026. Kimi K2.5 came out Jan 27, 2026; o3-pro came out Jun 10, 2025. Knowledge cutoff: Kimi K2.5 Jan 2025, o3-pro May 2024.
How do you decide the winner?
This rating uses capability (59%, independent benchmark results); price (29%, blended price per million tokens (3 input : 1 output), log scale); context window (12%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.This rating uses capability (83%, independent benchmark results); context window (17%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.