Nemotron 3 Super 120B A12B vs Sarvam 105B vs Solar Pro 3
Too close to call on our weighted score (Nemotron 3 Super 120B A12B 54, Solar Pro 3 53, Sarvam 105B 52). The right pick depends on what you value most.
NVIDIANemotron 3 Super 120B A12B
54/100- ECI—
- Price$0.15 / $0.65
- Context262K
Sarvam AI
Sarvam 105B
52/100- ECI—
- Price$0.158 / $0.632
- Context131K
UpstageSolar Pro 3
53/100- ECI—
- Price$0.25 / $0.25
- Context131K
Too close to call
It is close. Our weighted score puts them within 1 points (Nemotron 3 Super 120B A12B 54/100, Solar Pro 3 53/100, Sarvam 105B 52/100), so choose by what matters most for your work: Solar Pro 3 on price and Nemotron 3 Super 120B A12B for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceSolar Pro 3Solar Pro 3 $0.25 · Nemotron 3 Super 120B A12B $0.275 · Sarvam 105B $0.276 per 1M tokens (3:1 blend)
- Longest contextNemotron 3 Super 120B A12BNemotron 3 Super 120B A12B 262,144 · Sarvam 105B 131,072 · Solar Pro 3 131,072 tokens
- Widest inputsSame inputsNemotron 3 Super 120B A12B: Text · Sarvam 105B: Text · Solar Pro 3: Text
- Self-hostingNemotron 3 Super 120B A12B and Sarvam 105BPublishes downloadable weights
| Measure | Weight | Nemotron 3 Super 120B A12B | Sarvam 105B | Solar Pro 3 |
|---|---|---|---|---|
| Price | 50% | 73 | 73 | 75 |
| Inputs & features | 30% | 35 | 35 | 35 |
| Context window | 20% | 37 | 25 | 25 |
| Overall | 100% | 54/100 | 52/100 | 53/100 |
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 | Nemotron 3 Super 120B A12BNVIDIA | Sarvam 105BSarvam AI | Solar Pro 3Upstage |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.15 (best) | $0.158 | $0.25 |
| Output | $0.65 | $0.632 | $0.25 (best) |
| Cached input | — | $0.053 | — |
| Blended (3:1) | $0.275 | $0.276 | $0.25 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 16 providers | Official Sarvam AI API | Official Upstage API |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 131,072 tokens |
| Max output | 262,144 tokens (best) | 131,072 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yeslow · medium · high | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | — | sarvam-105b | solar-pro3 |
| API providers | 18 (best) | 3 | 4 |
| Released | Mar 11, 2026 | Feb 18, 2026 | Jan 26, 2026 |
| Knowledge cutoff | Jun 2025 | — | Jul 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 Super 120B A12B$2.80
- Sarvam 105B$2.84
- Solar Pro 3$3.00
Which should you choose?
Which is better: Nemotron 3 Super 120B A12B, Sarvam 105B or Solar Pro 3?
It is close. Our weighted score puts them within 1 points (Nemotron 3 Super 120B A12B 54/100, Solar Pro 3 53/100, Sarvam 105B 52/100), so choose by what matters most for your work: Solar Pro 3 on price and Nemotron 3 Super 120B A12B for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. 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, Sarvam 105B or Solar Pro 3?
Solar Pro 3 is cheaper at $0.25 input / $0.25 output per million tokens (official Upstage API price). Nemotron 3 Super 120B A12B costs $0.15 input / $0.65 output per million tokens (median across 16 API providers); Sarvam 105B costs $0.158 input / $0.632 output per million tokens (official Sarvam AI API price). At a typical mix of three input tokens to one output token, that is $0.25 per million tokens for Solar Pro 3 versus $0.275 for Nemotron 3 Super 120B A12B (1.1× as much) and $0.276 for Sarvam 105B (1.1× 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, Sarvam 105B has not been scored yet and Solar Pro 3 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Nemotron 3 Super 120B A12B, Sarvam 105B and Solar Pro 3 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?
Nemotron 3 Super 120B A12B has the largest context window at 262,144 tokens, against 131,072 for Sarvam 105B and 131,072 for Solar Pro 3. Maximum output per response: Nemotron 3 Super 120B A12B up to 262,144, Sarvam 105B up to 131,072, Solar Pro 3 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Nemotron 3 Super 120B A12B accepts text; Sarvam 105B accepts text; Solar Pro 3 accepts text. They handle the same number of input types.
Are any of these open source?
Nemotron 3 Super 120B A12B and Sarvam 105B publishes its weights and can be self-hosted; Solar Pro 3 is proprietary.
Which is newer?
Nemotron 3 Super 120B A12B is the newest, released Mar 11, 2026. Sarvam 105B came out Feb 18, 2026; Solar Pro 3 came out Jan 26, 2026. Knowledge cutoff: Nemotron 3 Super 120B A12B Jun 2025, Solar Pro 3 Jul 2025.
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 Nov 2, 2026.
