Nemotron 3 Ultra 550B A55B vs Qwen3 235B-A22B Thinking 2507 vs Qwen3.5 Plus
Qwen3.5 Plus comes out ahead, 74 to 67 and 60 on our weighted score, and it is the cheaper option too.
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 235B-A22B Thinking 2507
60/100- ECI143.3
- Price$0.30 / $2.90
- Context262K
- Our pick
Alibaba (Qwen)
Qwen3.5 Plus
74/100- ECI147.3
- Price$0.40 / $2.40
- Context1M
Qwen3.5 Plus is our pick
Qwen3.5 Plus is the better all-round choice, scoring 74/100 against Nemotron 3 Ultra 550B A55B (67) and Qwen3 235B-A22B Thinking 2507 (60). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityQwen3.5 PlusCapabilities Index (ECI): Qwen3.5 Plus 147.3 · Nemotron 3 Ultra 550B A55B 147.0 · Qwen3 235B-A22B Thinking 2507 143.3
- Lowest priceQwen3.5 PlusQwen3.5 Plus $0.90 · Qwen3 235B-A22B Thinking 2507 $0.95 · Nemotron 3 Ultra 550B A55B $1.01 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 235B-A22B Thinking 2507 262,144 tokens
- Widest inputsQwen3.5 PlusNemotron 3 Ultra 550B A55B: Text · Qwen3 235B-A22B Thinking 2507: Text · Qwen3.5 Plus: Text, Images, Video
- Self-hostingNemotron 3 Ultra 550B A55B and Qwen3 235B-A22B Thinking 2507Publishes downloadable weights (Apache 2.0)
| Measure | Weight | Nemotron 3 Ultra 550B A55B | Qwen3 235B-A22B Thinking 2507 | Qwen3.5 Plus |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 74 | 71 | 75 |
| Inputs & features | 20% | 45 | 35 | 80 |
| Context window | 13% | 64 | 43 | 64 |
| Overall | 100% | 67/100 | 60/100 | 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 | 143.3 | 147.3 (best) |
| ECI rank | #82 of 158 | #100 of 158 | #80 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 85.4% (best) | 80.1% | 84.9% |
| OTIS Mock AIME 2024–2025Competition mathematics | 86.7% | 86.7% | 86.7% |
| SimpleQA VerifiedShort factual questions | — | 40.4% (best) | 25.4% |
| Price per million tokens | |||
| Input | $0.55 | $0.30 (best) | $0.40 |
| Output | $2.40 (best) | $2.90 | $2.40 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $1.01 | $0.95 | $0.90 (best) |
| Long-context rate | Same rate | Same rate | Over 256K: $0.50 / $3.00 |
| Price source | Median of 20 providers | Median of 11 providers | 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) | 81,920 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yesmedium · high | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Open | OpenApache 2.0 | Proprietary |
| API model ID | nvidia/nemotron-3-ultra-550b-a55b | — | qwen3.5-plus |
| API providers | 26 (best) | 12 | 14 |
| Released | Jun 4, 2026 | Jul 25, 2025 | 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 235B-A22B Thinking 2507$8.80
Qwen3.5 Plus$8.80
Which should you choose?
Which is better: Nemotron 3 Ultra 550B A55B, Qwen3 235B-A22B Thinking 2507 or Qwen3.5 Plus?
Qwen3.5 Plus is the better all-round choice, scoring 74/100 against Nemotron 3 Ultra 550B A55B (67) and Qwen3 235B-A22B Thinking 2507 (60). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Nemotron 3 Ultra 550B A55B, Qwen3 235B-A22B Thinking 2507 or Qwen3.5 Plus?
Qwen3.5 Plus is cheaper at $0.40 input / $2.40 output per million tokens (official Alibaba API price). Qwen3 235B-A22B Thinking 2507 costs $0.30 input / $2.90 output per million tokens (median across 11 API providers); Nemotron 3 Ultra 550B A55B costs $0.55 input / $2.40 output per million tokens (median across 20 API providers; free on Nvidia). At a typical mix of three input tokens to one output token, that is $0.90 per million tokens for Qwen3.5 Plus versus $0.95 for Qwen3 235B-A22B Thinking 2507 (1.1× as much) and $1.01 for Nemotron 3 Ultra 550B A55B (1.1× as much).
Which scores higher on benchmarks?
Qwen3.5 Plus scores higher on the Capabilities Index (ECI): Qwen3.5 Plus 147.3 (#80 of 158), Nemotron 3 Ultra 550B A55B 147.0 (#82 of 158) and Qwen3 235B-A22B Thinking 2507 143.3 (#100 of 158). The confidence ranges of the top two overlap (145.4–149.2 vs 145.0–149.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Nemotron 3 Ultra 550B A55B 85.4%, Qwen3.5 Plus 84.9%, Qwen3 235B-A22B Thinking 2507 80.1%; OTIS Mock AIME 2024–2025 — Nemotron 3 Ultra 550B A55B 86.7%, Qwen3 235B-A22B Thinking 2507 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 235B-A22B Thinking 2507 and Qwen3.5 Plus yet, so there is no like-for-like coding score. On overall capability, Qwen3.5 Plus 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 235B-A22B Thinking 2507. Maximum output per response: Nemotron 3 Ultra 550B A55B up to 128,000, Qwen3 235B-A22B Thinking 2507 up to 81,920, Qwen3.5 Plus up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Nemotron 3 Ultra 550B A55B accepts text; Qwen3 235B-A22B Thinking 2507 accepts text; Qwen3.5 Plus accepts text, images and video. Qwen3.5 Plus handles the widest range of inputs.
Are any of these open source?
Nemotron 3 Ultra 550B A55B and Qwen3 235B-A22B Thinking 2507 publishes its weights (Apache 2.0) 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 235B-A22B Thinking 2507 came out Jul 25, 2025. 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.