Nemotron 3 Ultra 550B A55B vs Qwen3.5 397B-A17B vs Qwen3.5 Plus
Too close to call on our weighted score (Qwen3.5 Plus 74, Qwen3.5 397B-A17B 72, Nemotron 3 Ultra 550B A55B 67). The right pick depends on what you value most.
Price in rating: Excluded · Include price
NVIDIA
Nemotron 3 Ultra 550B A55B
67/100- ECI147.0
- Price$0.55 / $2.40
- Context1M
Alibaba (Qwen)
Qwen3.5 397B-A17B
72/100- ECI148.0
- Price$0.60 / $3.60
- Context262K
Alibaba (Qwen)
Qwen3.5 Plus
74/100- ECI147.3
- Price$0.40 / $2.40
- Context1M
Too close to call
It is close. Our weighted score puts them within 2 points (Qwen3.5 Plus 74/100, Qwen3.5 397B-A17B 72/100, Nemotron 3 Ultra 550B A55B 67/100), so choose by what matters most for your work: Qwen3.5 397B-A17B for raw capability and Qwen3.5 Plus on price. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityQwen3.5 397B-A17BCapabilities Index (ECI): Qwen3.5 397B-A17B 148.0 · Qwen3.5 Plus 147.3 · Nemotron 3 Ultra 550B A55B 147.0
- Lowest priceQwen3.5 PlusQwen3.5 Plus $0.90 · Nemotron 3 Ultra 550B A55B $1.01 · Qwen3.5 397B-A17B $1.35 per 1M tokens (3:1 blend)
- Longest contextNemotron 3 Ultra 550B A55B and Qwen3.5 PlusNemotron 3 Ultra 550B A55B 1,000,000 · Qwen3.5 Plus 1,000,000 · Qwen3.5 397B-A17B 262,144 tokens
- Widest inputsQwen3.5 397B-A17B and Qwen3.5 PlusNemotron 3 Ultra 550B A55B: Text · Qwen3.5 397B-A17B: Text, Images, Video · Qwen3.5 Plus: Text, Images, Video
- Self-hostingNemotron 3 Ultra 550B A55B and Qwen3.5 397B-A17BPublishes downloadable weights
| Measure | Weight | Nemotron 3 Ultra 550B A55B | Qwen3.5 397B-A17B | Qwen3.5 Plus |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 74 | 75 | 75 |
| Inputs & features | 20% | 45 | 80 | 80 |
| Context window | 13% | 64 | 43 | 64 |
| Overall | 100% | 67/100 | 72/100 | 74/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 147.0 | 148.0 (best) | 147.3 |
| ECI rank | #82 of 158 | #76 of 158 (best) | #80 of 158 |
| GPQA DiamondGraduate-level science questions | 85.4% | 86.4% (best) | 84.9% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 31.2% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 86.7% | 88.9% (best) | 86.7% |
| SimpleQA VerifiedShort factual questions | — | — | 25.4% |
| Price per million tokens | |||
| Input | $0.55 | $0.60 | $0.40 (best) |
| Output | $2.40 (best) | $3.60 | $2.40 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $1.01 | $1.35 | $0.90 (best) |
| Long-context rate | Same rate | Same rate | Over 256K: $0.50 / $3.00 |
| Price source | Median of 20 providers | Official Alibaba API | Official Alibaba API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 262,144 tokens | 1,000,000 tokens (best) |
| Max output | 128,000 tokens (best) | 65,536 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | Yes |
| Reasoning | Yesmedium · high | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | nvidia/nemotron-3-ultra-550b-a55b | qwen3.5-397b-a17b | qwen3.5-plus |
| API providers | 26 | 36 (best) | 14 |
| Released | Jun 4, 2026 | Feb 15, 2026 | Feb 16, 2026 |
| Knowledge cutoff | Sep 2025 | — | Apr 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Nemotron 3 Ultra 550B A55B$10.30
Qwen3.5 397B-A17B$13.20
Qwen3.5 Plus$8.80
Which should you choose?
Which is better: Nemotron 3 Ultra 550B A55B, Qwen3.5 397B-A17B or Qwen3.5 Plus?
It is close. Our weighted score puts them within 2 points (Qwen3.5 Plus 74/100, Qwen3.5 397B-A17B 72/100, Nemotron 3 Ultra 550B A55B 67/100), so choose by what matters most for your work: Qwen3.5 397B-A17B for raw capability and Qwen3.5 Plus on price. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Nemotron 3 Ultra 550B A55B, Qwen3.5 397B-A17B or Qwen3.5 Plus?
Qwen3.5 Plus is cheaper at $0.40 input / $2.40 output per million tokens (official Alibaba API price). Nemotron 3 Ultra 550B A55B costs $0.55 input / $2.40 output per million tokens (median across 20 API providers; free on Nvidia); 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 $0.90 per million tokens for Qwen3.5 Plus versus $1.01 for Nemotron 3 Ultra 550B A55B (1.1× as much) and $1.35 for Qwen3.5 397B-A17B (1.5× as much).
Which scores higher on benchmarks?
Qwen3.5 397B-A17B scores higher on the Capabilities Index (ECI): Qwen3.5 397B-A17B 148.0 (#76 of 158), Qwen3.5 Plus 147.3 (#80 of 158) and Nemotron 3 Ultra 550B A55B 147.0 (#82 of 158). The confidence ranges of the top two overlap (145.8–150.1 vs 145.4–149.2), so treat the gap as small. On individual benchmarks: GPQA Diamond — Qwen3.5 397B-A17B 86.4%, Nemotron 3 Ultra 550B A55B 85.4%, Qwen3.5 Plus 84.9%; OTIS Mock AIME 2024–2025 — Qwen3.5 397B-A17B 88.9%, Nemotron 3 Ultra 550B A55B 86.7%, Qwen3.5 Plus 86.7%.
Which is better for coding?
There are no published SWE-bench Verified results for Nemotron 3 Ultra 550B A55B, Qwen3.5 397B-A17B and Qwen3.5 Plus yet, so there is no like-for-like coding score. On overall capability, Qwen3.5 397B-A17B 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 and Qwen3.5 Plus have the largest context windows (1,000,000 and 1,000,000 tokens), against 262,144 for Qwen3.5 397B-A17B. Maximum output per response: Nemotron 3 Ultra 550B A55B up to 128,000, Qwen3.5 397B-A17B up to 65,536, Qwen3.5 Plus up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Nemotron 3 Ultra 550B A55B accepts text; Qwen3.5 397B-A17B accepts text, images and video; Qwen3.5 Plus accepts text, images and video. Qwen3.5 397B-A17B handles the widest range of inputs.
Are any of these open source?
Nemotron 3 Ultra 550B A55B and Qwen3.5 397B-A17B publishes its weights and can be self-hosted; Qwen3.5 Plus is proprietary.
Which is newer?
Nemotron 3 Ultra 550B A55B is the newest, released Jun 4, 2026. Qwen3.5 Plus came out Feb 16, 2026; Qwen3.5 397B-A17B came out Feb 15, 2026. Knowledge cutoff: Nemotron 3 Ultra 550B A55B Sep 2025, Qwen3.5 Plus Apr 2025.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.