Nemotron 3 Super 120B A12B vs openPangu 2.0 Flash vs Seed Character
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
NVIDIA
Nemotron 3 Super 120B A12B
38/100- ECI—
- Price$0.135 / $0.625
- Context262K
Huawei
openPangu 2.0 Flash
43/100- ECI—
- Price$0.12 / $0.24
- Context524K
ByteDance Seed
Seed Character
65/100- ECI—
- Price$0.119 / $0.297
- Context256K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Seed Character 65/100, openPangu 2.0 Flash 43/100, Nemotron 3 Super 120B A12B 38/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceopenPangu 2.0 FlashopenPangu 2.0 Flash $0.15 · Seed Character $0.163 · Nemotron 3 Super 120B A12B $0.258 per 1M tokens (3:1 blend)
- Longest contextopenPangu 2.0 FlashopenPangu 2.0 Flash 524,288 · Nemotron 3 Super 120B A12B 262,144 · Seed Character 256,000 tokens
- Widest inputsSeed CharacterNemotron 3 Super 120B A12B: Text · openPangu 2.0 Flash: Text · Seed Character: Text, Images, Video
- Self-hostingNemotron 3 Super 120B A12B and openPangu 2.0 FlashPublishes downloadable weights
| Measure | Weight | Nemotron 3 Super 120B A12B | openPangu 2.0 Flash | Seed Character |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 35 | 80 |
| Context window | 40% | 43 | 54 | 43 |
| Specs only | 100% | 38/100 | 43/100 | 65/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | openPangu 2.0 FlashHuawei | ||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.135 | $0.12 | $0.119 (best) |
| Output | $0.625 | $0.24 (best) | $0.297 |
| Cached input | — | — | $0.024 |
| Blended (3:1) | $0.258 | $0.15 (best) | $0.163 |
| Long-context rate | Same rate | Same rate | Over 32K: $0.178 / $0.891 |
| Price source | Median of 16 providers | Median of 1 providers | Official Volcengine Ark API |
| Limits | |||
| Context window | 262,144 tokens | 524,288 tokens (best) | 256,000 tokens |
| Max output | 262,144 tokens (best) | 131,072 tokens | 256,000 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 | Yes | Yes | Yesminimal · low · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | — | — | doubao-seed-character-260628 |
| API providers | 18 (best) | 1 | 3 |
| Released | Mar 11, 2026 | Jun 30, 2026 | Jun 23, 2026 |
| Knowledge cutoff | Jun 2025 | Jun 2026 | — |
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 Super 120B A12B$2.60
- openPangu 2.0 Flash$1.68
Seed Character$1.78
Which should you choose?
Which is better: Nemotron 3 Super 120B A12B, openPangu 2.0 Flash or Seed Character?
There is not enough shared capability evidence to name an overall winner. The scores (Seed Character 65/100, openPangu 2.0 Flash 43/100, Nemotron 3 Super 120B A12B 38/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Nemotron 3 Super 120B A12B, openPangu 2.0 Flash or Seed Character?
openPangu 2.0 Flash is cheaper at $0.12 input / $0.24 output per million tokens (median across 1 API provider). Seed Character costs $0.119 input / $0.297 output per million tokens (official Volcengine Ark API price); Nemotron 3 Super 120B A12B costs $0.135 input / $0.625 output per million tokens (median across 16 API providers). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for openPangu 2.0 Flash versus $0.163 for Seed Character (1.1× as much) and $0.258 for Nemotron 3 Super 120B A12B (1.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Nemotron 3 Super 120B A12B has not been scored yet, openPangu 2.0 Flash has not been scored yet and Seed Character has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Nemotron 3 Super 120B A12B, openPangu 2.0 Flash and Seed Character yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
openPangu 2.0 Flash has the largest context window at 524,288 tokens, against 262,144 for Nemotron 3 Super 120B A12B and 256,000 for Seed Character. Maximum output per response: Nemotron 3 Super 120B A12B up to 262,144, openPangu 2.0 Flash up to 131,072, Seed Character up to 256,000 tokens.
Which can read images, PDFs, audio or video?
Nemotron 3 Super 120B A12B accepts text; openPangu 2.0 Flash accepts text; Seed Character accepts text, images and video. Seed Character handles the widest range of inputs.
Are any of these open source?
Nemotron 3 Super 120B A12B and openPangu 2.0 Flash publishes its weights and can be self-hosted; Seed Character is proprietary.
Which is newer?
openPangu 2.0 Flash is the newest, released Jun 30, 2026. Seed Character came out Jun 23, 2026; Nemotron 3 Super 120B A12B came out Mar 11, 2026. Knowledge cutoff: Nemotron 3 Super 120B A12B Jun 2025, openPangu 2.0 Flash Jun 2026.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.