Qwen3.6 35B-A3B vs Nemotron 3 Ultra 550B A55B vs MiniMax-M2.7
Qwen3.6 35B-A3B comes out ahead, 68 to 62 and 61 on our weighted score, though MiniMax-M2.7 is 6% cheaper per token.
- Our pick
Alibaba (Qwen)Qwen3.6 35B-A3B
68/100- ECI143.9
- Price$0.248 / $1.49
- Context262K
NVIDIANemotron 3 Ultra 550B A55B
62/100- ECI146.2
- Price$0.50 / $2.50
- Context1M
MiniMaxMiniMax-M2.7
61/100- ECI145.9
- Price$0.30 / $1.20
- Context205K
Qwen3.6 35B-A3B is our pick
Qwen3.6 35B-A3B is the better all-round choice, scoring 68/100 against Nemotron 3 Ultra 550B A55B (62) and MiniMax-M2.7 (61). It leads on inputs & features. Nemotron 3 Ultra 550B A55B wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityNemotron 3 Ultra 550B A55BCapabilities Index (ECI): Nemotron 3 Ultra 550B A55B 146.2 · MiniMax-M2.7 145.9 · Qwen3.6 35B-A3B 143.9
- Lowest priceMiniMax-M2.7MiniMax-M2.7 $0.525 · Qwen3.6 35B-A3B $0.557 · Nemotron 3 Ultra 550B A55B $1.00 per 1M tokens (3:1 blend)
- Longest contextNemotron 3 Ultra 550B A55BNemotron 3 Ultra 550B A55B 1,000,000 · Qwen3.6 35B-A3B 262,144 · MiniMax-M2.7 204,800 tokens
- Widest inputsQwen3.6 35B-A3BQwen3.6 35B-A3B: Text, Images, Audio, Video · Nemotron 3 Ultra 550B A55B: Text · MiniMax-M2.7: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Qwen3.6 35B-A3B | Nemotron 3 Ultra 550B A55B | MiniMax-M2.7 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 70 | 73 | 73 |
| Price | 25% | 62 | 50 | 63 |
| Inputs & features | 15% | 90 | 45 | 35 |
| Context window | 10% | 37 | 60 | 32 |
| Overall | 100% | 68/100 | 62/100 | 61/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Qwen3.6 35B-A3BAlibaba (Qwen) | Nemotron 3 Ultra 550B A55BNVIDIA | MiniMax-M2.7MiniMax |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 143.9 | 146.2 (best) | 145.9 |
| ECI rank | #83 of 148 | #70 of 148 (best) | #73 of 148 |
| GPQA DiamondGraduate-level science questions | 84.9% | 85.4% (best) | — |
| FrontierMath Tiers 1–3Research-level mathematics | 20.4% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 86.7% | 86.7% | — |
| Price per million tokens | |||
| Input | $0.248 (best) | $0.50 | $0.30 |
| Output | $1.49 | $2.50 | $1.20 (best) |
| Cached input | — | $0.15 | $0.06 (best) |
| Blended (3:1) | $0.557 | $1.00 | $0.525 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official Nvidia API | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 262,144 tokens | 1,000,000 tokens (best) | 204,800 tokens |
| Max output | 65,536 tokens | 128,000 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | qwen3.6-35b-a3b | nvidia/nemotron-3-ultra-550b-a55b | MiniMax-M2.7 |
| API providers | 34 (best) | 21 | 29 |
| Released | Apr 17, 2026 | Jun 4, 2026 | Mar 18, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen3.6 35B-A3B$5.45
- Nemotron 3 Ultra 550B A55B$10.00
- MiniMax-M2.7$5.40
Which should you choose?
Which is better: Qwen3.6 35B-A3B, Nemotron 3 Ultra 550B A55B or MiniMax-M2.7?
Qwen3.6 35B-A3B is the better all-round choice, scoring 68/100 against Nemotron 3 Ultra 550B A55B (62) and MiniMax-M2.7 (61). It leads on inputs & features. Nemotron 3 Ultra 550B A55B wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Qwen3.6 35B-A3B, Nemotron 3 Ultra 550B A55B or MiniMax-M2.7?
MiniMax-M2.7 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3.6 35B-A3B costs $0.248 input / $1.49 output per million tokens (official Alibaba API price); Nemotron 3 Ultra 550B A55B costs $0.50 input / $2.50 output per million tokens (official Nvidia API price). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M2.7 versus $0.557 for Qwen3.6 35B-A3B (1.1× as much) and $1.00 for Nemotron 3 Ultra 550B A55B (1.9× as much).
Which scores higher on benchmarks?
Nemotron 3 Ultra 550B A55B scores higher on the Capabilities Index (ECI): Nemotron 3 Ultra 550B A55B 146.2 (#70 of 148), MiniMax-M2.7 145.9 (#73 of 148) and Qwen3.6 35B-A3B 143.9 (#83 of 148). The confidence ranges of the top two overlap (143.9–148.1 vs 138.2–148.0), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.6 35B-A3B, Nemotron 3 Ultra 550B A55B and MiniMax-M2.7 yet, so there is no like-for-like coding score. On overall capability, Nemotron 3 Ultra 550B A55B 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 Qwen3.6 35B-A3B and 204,800 for MiniMax-M2.7. Maximum output per response: Qwen3.6 35B-A3B up to 65,536, Nemotron 3 Ultra 550B A55B up to 128,000, MiniMax-M2.7 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Qwen3.6 35B-A3B accepts text, images, audio and video; Nemotron 3 Ultra 550B A55B accepts text; MiniMax-M2.7 accepts text. Qwen3.6 35B-A3B 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. Qwen3.6 35B-A3B came out Apr 17, 2026; MiniMax-M2.7 came out Mar 18, 2026.
How do you decide the winner?
Each model gets a 0–100 score on 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 Oct 4, 2026.
Related comparisons
- Qwen3.6 35B-A3B vs GPT-5.4 nanoOpenAI · ECI 145.8
- Qwen3.6 35B-A3B vs Gemini 3.5 Flash LiteGoogle · ECI 145.1
- Qwen3.6 35B-A3B vs GLM-4.7Z.ai (Zhipu) · ECI 143.5
- Nemotron 3 Ultra 550B A55B vs Qwen3.6 27BAlibaba (Qwen) · ECI 146.5
- Nemotron 3 Ultra 550B A55B vs Gemini 3.5 Flash LiteGoogle · ECI 145.1
- Nemotron 3 Ultra 550B A55B vs Kimi K2 ThinkingMoonshot AI · ECI 146.0
