# Inkling 2 Small vs Nemotron 3 Ultra

> Side-by-side benchmark comparison for Inkling 2 Small and Nemotron 3 Ultra across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/inkling-2-small-vs-nemotron-3-ultra
- Last updated: November 7, 2026

- Shared sourced benchmarks: 8
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Inkling 2 Small leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Inkling 2 Small has the higher overall point estimate 59.06 to 46.67. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in coding, where the averages are 59.7 for Inkling 2 Small and 22.6 for Nemotron 3 Ultra.
- The biggest single benchmark swing is BrowseComp in Agentic, with scores of 90.2% and 44.4%.
- Nemotron 3 Ultra is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Inkling 2 Small | Nemotron 3 Ultra |
|----------|----------|----------|
| Creator | Thinking Machines Lab | NVIDIA |
| Type | Proprietary | Open Weight |
| Reasoning | Hybrid | Reasoning |
| Context | 1M | 1M |
| Overall Score | 59.06 | 46.67 |
| Benchmarks Covered | 25 | 25 |
| Pricing (input/output) | $0.30 / $1.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Inkling 2 Small
- Inkling 2 Small public-lane score: 59.9 (Supported · #26/131)
- Nemotron 3 Ultra public-lane score: 24.9 (Supported · #111/131)

| Benchmark | Inkling 2 Small | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 85.1% | 56.4% | Inkling 2 Small |
| BrowseComp | 90.2% | 44.4% | Inkling 2 Small |
| DeepSearchQA | 90.9% | Coming soon | Coming soon |
| MCP Atlas | 85% | Coming soon | Coming soon |
| JobBench | 70.5% | Coming soon | Coming soon |
| PinchBench | Coming soon | 90.0% | Coming soon |
| τ³-bench results | Coming soon | 70.9% | Coming soon |
| HLE w/ tools | Coming soon | 37.4% | Coming soon |
| Terminal-Bench 2.1 (Vals) | Coming soon | 50.9% | Coming soon |
| MazeBench | Coming soon | 0% | Coming soon |

### Coding

- Winner: Inkling 2 Small
- Inkling 2 Small public-lane score: 59.7 (Supported · #20/157)
- Nemotron 3 Ultra public-lane score: 22.6 (Supported · #130/157)

| Benchmark | Inkling 2 Small | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 82.2% | 71.9% | Inkling 2 Small |
| SWE Multilingual | 81.2% | 67.7% | Inkling 2 Small |
| sweMarathon | 38.8% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 85.1% | 56.4% | Inkling 2 Small |
| DeepSWE | 72.1% | Coming soon | Coming soon |
| PostTrainBench v1.2 | 31.9% | Coming soon | Coming soon |
| LiveCodeBench v6 | Coming soon | 89.0% | Coming soon |
| SciCode | Coming soon | 44.6% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 86.0% | Coming soon |
| SWE-bench (Vals) | Coming soon | 69.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- Inkling 2 Small public-lane score: 86.1 (Unranked · 2 rankable rows)
- Nemotron 3 Ultra public-lane score: 60.3 (Unranked · 1 rankable row)

| Benchmark | Inkling 2 Small | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 70.6% | 61.9% | Inkling 2 Small |
| CritPt | Coming soon | 3.1% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Inkling 2 Small public-lane score: 86.6 (#12/59)
- Nemotron 3 Ultra public-lane score: Coming soon

| Benchmark | Inkling 2 Small | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 87.7% | Coming soon | Coming soon |
| CharXiv w/o tools | 85.6% | Coming soon | Coming soon |
| Chartography (no tools) | 36.7% | Coming soon | Coming soon |
| Chartography (tools) | 80.4% | Coming soon | Coming soon |
| BabyVision | 68.6% | Coming soon | Coming soon |
| BabyVision w/ Python | 93.7% | Coming soon | Coming soon |
| ScreenSpot Pro | 83.8% | Coming soon | Coming soon |
| PerceptionBench | 64.7% | Coming soon | Coming soon |
| MathVision | 92.8% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- Inkling 2 Small public-lane score: 60.4 (Estimated · #46/178)
- Nemotron 3 Ultra public-lane score: 50.2 (Estimated · #81/178)

| Benchmark | Inkling 2 Small | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 93% | 87% | Inkling 2 Small |
| GPQA-D | 93.0% | 87.0% | Inkling 2 Small |
| HLE | Coming soon | 26.7% | Coming soon |
| HLE w/o tools | Coming soon | 26.7% | Coming soon |
| MMLU-Pro | Coming soon | 86.8% | Coming soon |
| GPQA Diamond (Vals) | Coming soon | 86.1% | Coming soon |
| MMLU-Pro (Vals) | Coming soon | 85.8% | Coming soon |

### Multilingual

- Winner: Not comparable
- Inkling 2 Small public-lane score: Coming soon
- Nemotron 3 Ultra public-lane score: 89.2 (#7/17)

| Benchmark | Inkling 2 Small | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 83% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Inkling 2 Small public-lane score: Coming soon
- Nemotron 3 Ultra public-lane score: 92.1 (#21/157)

| Benchmark | Inkling 2 Small | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 81.7% | Coming soon |

### Mathematics

- Winner: Not comparable
- Inkling 2 Small public-lane score: 85.9 (Unranked · 2 rankable rows)
- Nemotron 3 Ultra public-lane score: Coming soon

| Benchmark | Inkling 2 Small | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2026 | 95.8% | Coming soon | Coming soon |
| Apex | 63.5% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Inkling 2 Small or Nemotron 3 Ultra?

Inkling 2 Small has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Inkling 2 Small and Nemotron 3 Ultra?

The widest category gap is in coding, where the averages are 59.7 for Inkling 2 Small and 22.6 for Nemotron 3 Ultra.

### How many benchmarks does Inkling 2 Small cover on BenchLM?

Inkling 2 Small currently has 25 sourced benchmark scores on BenchLM.

### How many benchmarks does Nemotron 3 Ultra cover on BenchLM?

Nemotron 3 Ultra currently has 25 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Inkling 2 Small vs Inkling-Small](/compare/inkling-2-small-vs-inkling-small)
- [Nemotron 3 Ultra vs Inkling-Small](/compare/inkling-small-vs-nemotron-3-ultra)
- [Inkling 2 Small vs Inkling](/compare/inkling-vs-inkling-2-small)
- [Nemotron 3 Ultra vs Inkling](/compare/inkling-vs-nemotron-3-ultra)

## Explore More

- [Inkling 2 Small profile](/models/inkling-2-small)
- [Nemotron 3 Ultra profile](/models/nemotron-3-ultra)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)