# Kimi K2.5 (Reasoning) vs Nemotron 3 Ultra

> Side-by-side benchmark comparison for Kimi K2.5 (Reasoning) and Nemotron 3 Ultra across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-k2-5-reasoning-vs-nemotron-3-ultra
- Last updated: October 15, 2026

- Shared sourced benchmarks: 6
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Kimi K2.5 (Reasoning) leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Kimi K2.5 (Reasoning) has the higher overall point estimate 56.26 to 47.12. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in agentic, where the averages are 38.8 for Kimi K2.5 (Reasoning) and 28 for Nemotron 3 Ultra.
- The biggest single benchmark swing is BrowseComp in Agentic, with scores of 60.6% and 44.4%.
- Nemotron 3 Ultra is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Nemotron 3 Ultra also has the larger context window at 1M.

## Model Snapshot

| Property | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra |
|----------|----------|----------|
| Creator | Moonshot AI | NVIDIA |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 1M |
| Overall Score | 56.26 | 47.12 |
| Benchmarks Covered | 15 | 24 |
| Pricing (input/output) | $0.60 / $3.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Kimi K2.5 (Reasoning) public-lane score: 38.8 (Estimated · #68/126)
- Nemotron 3 Ultra public-lane score: 28 (Supported · #95/126)

| Benchmark | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 50.8% | Coming soon | Coming soon |
| BrowseComp | 60.6% | 44.4% | Kimi K2.5 (Reasoning) |
| OSWorld-Verified | 63.3% | Coming soon | Coming soon |
| Gert Labs | 32.58% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 56.4% | 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 |

### Coding

- Winner: Not comparable
- Kimi K2.5 (Reasoning) public-lane score: Coming soon
- Nemotron 3 Ultra public-lane score: 21.9 (Supported · #115/149)

| Benchmark | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 76.8% | 71.9% | Kimi K2.5 (Reasoning) |
| LiveCodeBench v6 | 85.0% | 89.0% | Nemotron 3 Ultra |
| Terminal-Bench 2.0 | 50.8% | Coming soon | Coming soon |
| Vibe Code Bench | 17.54% | Coming soon | Coming soon |
| SWE Multilingual | Coming soon | 67.7% | Coming soon |
| SciCode | Coming soon | 44.6% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 56.4% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 86.0% | Coming soon |
| SWE-bench (Vals) | Coming soon | 69.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- Kimi K2.5 (Reasoning) public-lane score: 67.1 (Unranked · 1 rankable row)
- Nemotron 3 Ultra public-lane score: 70.8 (#20/29)

| Benchmark | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 61% | 61.9% | Nemotron 3 Ultra |
| CritPt | Coming soon | 3.1% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Kimi K2.5 (Reasoning) public-lane score: 69 (#33/54)
- Nemotron 3 Ultra public-lane score: Coming soon

| Benchmark | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 78.5% | Coming soon | Coming soon |
| CharXiv | 77.5% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- Kimi K2.5 (Reasoning) public-lane score: 49 (Estimated · #83/182)
- Nemotron 3 Ultra public-lane score: 50.3 (Estimated · #78/182)

| Benchmark | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87.6% | 87% | Kimi K2.5 (Reasoning) |
| MMLU-Pro | 87.1% | 86.8% | Kimi K2.5 (Reasoning) |
| GPQA-D | Coming soon | 87.0% | Coming soon |
| HLE | Coming soon | 26.7% | Coming soon |
| HLE w/o tools | Coming soon | 26.7% | Coming soon |
| GPQA Diamond (Vals) | Coming soon | 86.1% | Coming soon |
| MMLU-Pro (Vals) | Coming soon | 85.8% | Coming soon |

### Multilingual

- Winner: Not comparable
- Kimi K2.5 (Reasoning) public-lane score: Coming soon
- Nemotron 3 Ultra public-lane score: 89.2 (#7/17)

| Benchmark | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 83% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Kimi K2.5 (Reasoning) public-lane score: Coming soon
- Nemotron 3 Ultra public-lane score: 92.1 (#20/146)

| Benchmark | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 81.7% | Coming soon |

### Mathematics

- Winner: Not comparable
- Kimi K2.5 (Reasoning) public-lane score: Coming soon
- Nemotron 3 Ultra public-lane score: Coming soon

| Benchmark | Kimi K2.5 (Reasoning) | Nemotron 3 Ultra | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 96.1% | Coming soon | Coming soon |
| HMMT Feb 2025 | 95.4% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Kimi K2.5 (Reasoning) or Nemotron 3 Ultra?

Kimi K2.5 (Reasoning) has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Kimi K2.5 (Reasoning) and Nemotron 3 Ultra?

The widest category gap is in agentic, where the averages are 38.8 for Kimi K2.5 (Reasoning) and 28 for Nemotron 3 Ultra.

### How many benchmarks does Kimi K2.5 (Reasoning) cover on BenchLM?

Kimi K2.5 (Reasoning) currently has 15 sourced benchmark scores on BenchLM.

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

Nemotron 3 Ultra currently has 24 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Kimi K2.5 (Reasoning) vs Kimi K2.5](/compare/kimi-k2-5-vs-kimi-k2-5-reasoning)
- [Nemotron 3 Ultra vs Kimi K2.5](/compare/kimi-k2-5-vs-nemotron-3-ultra)
- [Kimi K2.5 (Reasoning) vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-k2-5-reasoning)
- [Nemotron 3 Ultra vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-nemotron-3-ultra)

## Explore More

- [Kimi K2.5 (Reasoning) profile](/models/kimi-k2-5-reasoning)
- [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)