# Nemotron 3 Ultra vs Trinity-Large-Thinking

> Side-by-side benchmark comparison for Nemotron 3 Ultra and Trinity-Large-Thinking across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/nemotron-3-ultra-vs-trinity-large-thinking
- Last updated: October 15, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Nemotron 3 Ultra and Trinity-Large-Thinking share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Nemotron 3 Ultra has the lower published output-token price.
- Nemotron 3 Ultra has the larger published context window at 1M.

## Model Snapshot

| Property | Nemotron 3 Ultra | Trinity-Large-Thinking |
|----------|----------|----------|
| Creator | NVIDIA | Arcee AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 512K |
| Independent public score (not head-to-head) | 47.12 | 34.5 |
| Benchmarks Covered | 24 | 7 |
| Pricing (input/output) | $0.00 / $0.00 | $0.25 / $0.90 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Nemotron 3 Ultra public-lane score: 28 (Supported · #95/126)
- Trinity-Large-Thinking public-lane score: 13.5 (Estimated · #115/126)

| Benchmark | Nemotron 3 Ultra | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 56.4% | Coming soon | Coming soon |
| PinchBench | 90.0% | Coming soon | Coming soon |
| BrowseComp | 44.4% | Coming soon | Coming soon |
| τ³-bench results | 70.9% | Coming soon | Coming soon |
| HLE w/ tools | 37.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 50.9% | Coming soon | Coming soon |
| τ²-bench Airline | Coming soon | 88.0% | Coming soon |
| Gert Labs | Coming soon | 32.55% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Nemotron 3 Ultra public-lane score: 21.9 (Supported · #115/149)
- Trinity-Large-Thinking public-lane score: 17.9 (Supported · #123/149)

| Benchmark | Nemotron 3 Ultra | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 71.9% | Coming soon | Coming soon |
| SWE Multilingual | 67.7% | Coming soon | Coming soon |
| LiveCodeBench v6 | 89.0% | Coming soon | Coming soon |
| SciCode | 44.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 56.4% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 86.0% | Coming soon | Coming soon |
| SWE-bench (Vals) | 69.0% | Coming soon | Coming soon |
| SWE-bench Verified* | Coming soon | 63.2% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Nemotron 3 Ultra public-lane score: 70.8 (#20/29)
- Trinity-Large-Thinking public-lane score: 52 (Unranked · 2 rankable rows)

| Benchmark | Nemotron 3 Ultra | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| CritPt | 3.1% | Coming soon | Coming soon |
| LongBench v2 | 61.9% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Nemotron 3 Ultra public-lane score: 50.3 (Estimated · #78/182)
- Trinity-Large-Thinking public-lane score: 34.2 (Estimated · #135/182)

| Benchmark | Nemotron 3 Ultra | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87% | Coming soon | Coming soon |
| GPQA-D | 87.0% | 76.3% | Nemotron 3 Ultra |
| HLE | 26.7% | Coming soon | Coming soon |
| HLE w/o tools | 26.7% | Coming soon | Coming soon |
| MMLU-Pro | 86.8% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 86.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 85.8% | Coming soon | Coming soon |
| MMLU-Pro (Arcee) | Coming soon | 83.4% | Coming soon |

### Multilingual

- Winner: Insufficient shared evidence
- Nemotron 3 Ultra public-lane score: 89.2 (#7/17)
- Trinity-Large-Thinking public-lane score: Coming soon

| Benchmark | Nemotron 3 Ultra | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 83% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Nemotron 3 Ultra public-lane score: 92.1 (#20/146)
- Trinity-Large-Thinking public-lane score: 28.9 (#130/146)

| Benchmark | Nemotron 3 Ultra | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 81.7% | 52.3% | Nemotron 3 Ultra |

### Mathematics

- Winner: Insufficient shared evidence
- Nemotron 3 Ultra public-lane score: Coming soon
- Trinity-Large-Thinking public-lane score: Coming soon

| Benchmark | Nemotron 3 Ultra | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| AIME25 (Arcee) | Coming soon | 96.3% | Coming soon |

## FAQ

### Is there enough evidence to pick between Nemotron 3 Ultra and Trinity-Large-Thinking?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Nemotron 3 Ultra vs Trinity-Large-Preview](/compare/nemotron-3-ultra-vs-trinity-large-preview)
- [Trinity-Large-Thinking vs Trinity-Large-Preview](/compare/trinity-large-preview-vs-trinity-large-thinking)
- [Nemotron 3 Ultra vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-nemotron-3-ultra)
- [Trinity-Large-Thinking vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-trinity-large-thinking)

## Explore More

- [Nemotron 3 Ultra profile](/models/nemotron-3-ultra)
- [Trinity-Large-Thinking profile](/models/trinity-large-thinking)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)