Qwen3.5 397B-A17B vs Nemotron 3 Ultra 550B A55B vs Kimi K2.5
Too close to call on our weighted score (Qwen3.5 397B-A17B 64, Kimi K2.5 64, Nemotron 3 Ultra 550B A55B 62). The right pick depends on what you value most.
Price in rating: Included · Exclude price
Alibaba (Qwen)
Qwen3.5 397B-A17B
64/100- ECI148.0
- Price$0.60 / $3.60
- Context262K
NVIDIA
Nemotron 3 Ultra 550B A55B
62/100- ECI147.0
- Price$0.55 / $2.40
- Context1M
Moonshot AI
Kimi K2.5
64/100- ECI148.8
- Price$0.60 / $3.00
- Context262K
Too close to call
It is close. Our weighted score puts them within a point (Qwen3.5 397B-A17B 64/100, Kimi K2.5 64/100, Nemotron 3 Ultra 550B A55B 62/100), so choose by what matters most for your work: Kimi K2.5 for raw capability, Nemotron 3 Ultra 550B A55B on price and Nemotron 3 Ultra 550B A55B for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityKimi K2.5Capabilities Index (ECI): Kimi K2.5 148.8 · Qwen3.5 397B-A17B 148.0 · Nemotron 3 Ultra 550B A55B 147.0
- Lowest priceNemotron 3 Ultra 550B A55BNemotron 3 Ultra 550B A55B $1.01 · Kimi K2.5 $1.20 · Qwen3.5 397B-A17B $1.35 per 1M tokens (3:1 blend)
- Longest contextNemotron 3 Ultra 550B A55BNemotron 3 Ultra 550B A55B 1,000,000 · Qwen3.5 397B-A17B 262,144 · Kimi K2.5 262,144 tokens
- Widest inputsQwen3.5 397B-A17B and Kimi K2.5Qwen3.5 397B-A17B: Text, Images, Video · Nemotron 3 Ultra 550B A55B: Text · Kimi K2.5: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Qwen3.5 397B-A17B | Nemotron 3 Ultra 550B A55B | Kimi K2.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 75 | 74 | 76 |
| Price | 25% | 42 | 48 | 44 |
| Inputs & features | 15% | 80 | 45 | 70 |
| Context window | 10% | 43 | 64 | 43 |
| Overall | 100% | 64/100 | 62/100 | 64/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 148.0 | 147.0 | 148.8 (best) |
| ECI rank | #76 of 158 | #82 of 158 | #73 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 86.4% | 85.4% | 87.6% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 31.2% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 88.9% | 86.7% | 92.2% (best) |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 73.8% |
| SimpleQA VerifiedShort factual questions | — | — | 34.3% |
| Price per million tokens | |||
| Input | $0.60 | $0.55 (best) | $0.60 |
| Output | $3.60 | $2.40 (best) | $3.00 |
| Cached input | — | — | — |
| Blended (3:1) | $1.35 | $1.01 (best) | $1.20 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Median of 20 providers | Median of 36 providers |
| Limits | |||
| Context window | 262,144 tokens | 1,000,000 tokens (best) | 262,144 tokens |
| Max output | 65,536 tokens | 128,000 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | No | Yes |
| Reasoning | Yes | Yesmedium · high | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | qwen3.5-397b-a17b | nvidia/nemotron-3-ultra-550b-a55b | — |
| API providers | 36 (best) | 26 | 36 (best) |
| Released | Feb 15, 2026 | Jun 4, 2026 | Jan 27, 2026 |
| Knowledge cutoff | — | Sep 2025 | Jan 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Qwen3.5 397B-A17B$13.20
Nemotron 3 Ultra 550B A55B$10.30
Kimi K2.5$12.00
Which should you choose?
Which is better: Qwen3.5 397B-A17B, Nemotron 3 Ultra 550B A55B or Kimi K2.5?
It is close. Our weighted score puts them within a point (Qwen3.5 397B-A17B 64/100, Kimi K2.5 64/100, Nemotron 3 Ultra 550B A55B 62/100), so choose by what matters most for your work: Kimi K2.5 for raw capability, Nemotron 3 Ultra 550B A55B on price and Nemotron 3 Ultra 550B A55B for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Qwen3.5 397B-A17B, Nemotron 3 Ultra 550B A55B or Kimi K2.5?
Nemotron 3 Ultra 550B A55B is cheaper at $0.55 input / $2.40 output per million tokens (median across 20 API providers; free on Nvidia). Kimi K2.5 costs $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). At a typical mix of three input tokens to one output token, that is $1.01 per million tokens for Nemotron 3 Ultra 550B A55B versus $1.20 for Kimi K2.5 (1.2× as much) and $1.35 for Qwen3.5 397B-A17B (1.3× as much).
Which scores higher on benchmarks?
Kimi K2.5 scores higher on the Capabilities Index (ECI): Kimi K2.5 148.8 (#73 of 158), Qwen3.5 397B-A17B 148.0 (#76 of 158) and Nemotron 3 Ultra 550B A55B 147.0 (#82 of 158). The confidence ranges of the top two overlap (147.3–150.4 vs 145.8–150.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Kimi K2.5 87.6%, Qwen3.5 397B-A17B 86.4%, Nemotron 3 Ultra 550B A55B 85.4%; OTIS Mock AIME 2024–2025 — Kimi K2.5 92.2%, Qwen3.5 397B-A17B 88.9%, Nemotron 3 Ultra 550B A55B 86.7%.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.5 397B-A17B and Nemotron 3 Ultra 550B A55B 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?
Nemotron 3 Ultra 550B A55B has the largest context window at 1,000,000 tokens, against 262,144 for Qwen3.5 397B-A17B and 262,144 for Kimi K2.5. Maximum output per response: Qwen3.5 397B-A17B up to 65,536, Nemotron 3 Ultra 550B A55B up to 128,000, Kimi K2.5 up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 397B-A17B accepts text, images and video; Nemotron 3 Ultra 550B A55B accepts text; Kimi K2.5 accepts text, images and video. Qwen3.5 397B-A17B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Nemotron 3 Ultra 550B A55B is the newest, released Jun 4, 2026. Qwen3.5 397B-A17B came out Feb 15, 2026; Kimi K2.5 came out Jan 27, 2026. Knowledge cutoff: Nemotron 3 Ultra 550B A55B Sep 2025, Kimi K2.5 Jan 2025.
How do you decide the winner?
This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 18, 2026.