Model comparison
Kimi K2.5 vs Nemotron 3 Nano Omni 30B A3B
Head-to-head evidence from 20 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Kimi K2.5 #60 (Supported); Nemotron 3 Nano Omni 30B A3B #159 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Kimi K2.5 and Nemotron 3 Nano Omni 30B A3B share 20 comparable benchmark results. 4 of 8 categories are comparable. 43 results are unique to Kimi K2.5; 9 to Nemotron 3 Nano Omni 30B A3B.
Updated July 27, 2026- Shared results
- 20
- Kimi K2.5 only
- 43
- Nemotron 3 Nano Omni 30B A3B only
- 9
- Comparable categories
- 4 / 8
Pick Kimi K2.5 if you want the stronger benchmark profile. Nemotron 3 Nano Omni 30B A3B only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 20 shared benchmark results across 7 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Kimi K2.5 is clearly ahead on the BenchAlign aggregate, 58.78 to 43.32. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Kimi K2.5's sharpest advantage is in coding, where it averages 59.4 against 32. The single biggest benchmark swing on the page is SciCode, 48.7% to 32%. Nemotron 3 Nano Omni 30B A3B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Kimi K2.5 is also the more expensive model on tokens at $0.60 input / $3.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Nemotron 3 Nano Omni 30B A3B. That is roughly Infinityx on output cost alone. Nemotron 3 Nano Omni 30B A3B is the reasoning model in the pair, while Kimi K2.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Kimi K2.5 | Δ | Nemotron 3 Nano Omni 30B A3B |
|---|---|---|---|
| Coding | Kimi K2.559.4 | Margin← 27.4 | Nemotron 3 Nano Omni 30B A3B32.0 |
| Inst. Following | Kimi K2.593.9 | Margin← 19.7 | Nemotron 3 Nano Omni 30B A3B74.2 |
| Knowledge | Kimi K2.556.9 | Margin→ 19.4 | Nemotron 3 Nano Omni 30B A3B76.3 |
| Multimodal | Kimi K2.578.5 | Margin← 2.2 | Nemotron 3 Nano Omni 30B A3B76.3 |
| Agentic | Kimi K2.555.0 | MarginNo overlap | Nemotron 3 Nano Omni 30B A3BNot measured |
| Reasoning | Kimi K2.561.0 | MarginNo overlap | Nemotron 3 Nano Omni 30B A3BNot measured |
| Math | Kimi K2.560.6 | MarginNo overlap | Nemotron 3 Nano Omni 30B A3BNot measured |
| Multilingual | Kimi K2.582.3 | MarginNo overlap | Nemotron 3 Nano Omni 30B A3BNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SciCode
CodingA 48.7%B 32%Winner: Kimi K2.5Δ 16.7SciCode: Kimi K2.5 scored 48.7%; Nemotron 3 Nano Omni 30B A3B scored 32%. Kimi K2.5 wins this benchmark. - Source ↗
GPQA
KnowledgeA 87.6%B 72.2%Winner: Kimi K2.5Δ 15.4GPQA: Kimi K2.5 scored 87.6%; Nemotron 3 Nano Omni 30B A3B scored 72.2%. Kimi K2.5 wins this benchmark. - Source ↗
MMLU-Pro
KnowledgeA 87.1%B 77.3%Winner: Kimi K2.5Δ 9.8MMLU-Pro: Kimi K2.5 scored 87.1%; Nemotron 3 Nano Omni 30B A3B scored 77.3%. Kimi K2.5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Kimi K2.5 | Nemotron 3 Nano Omni 30B A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Kimi K2.5$0.6 input / $3 output | Nemotron 3 Nano Omni 30B A3B$0 input / $0 output | Nemotron 3 Nano Omni 30B A3B has the lower combined listed price. |
| Generation speedtokens per second | Kimi K2.545 tok/s | Nemotron 3 Nano Omni 30B A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Kimi K2.52.38 s | Nemotron 3 Nano Omni 30B A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Kimi K2.5256K | Nemotron 3 Nano Omni 30B A3B256K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic20 benchmarks
| Benchmark | Kimi K2.5 | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 50.8% | — | Not comparable |
| BrowseCompSource | 60.6% | — | Not comparable |
| Claw-EvalSource | 52.3% | — | Not comparable |
| QwenClawBenchSource | 54.3% | — | Not comparable |
| τ³-bench resultsSource | 65.7% | — | Not comparable |
| DeepSearchQASource | 77.1% | — | Not comparable |
| DeepPlanningSource | 14.4% | — | Not comparable |
| ToolathlonSource | 27.8% | — | Not comparable |
| MCP AtlasSource | 29.5% | — | Not comparable |
| MCP-TasksSource | 59.1% | — | Not comparable |
| WideResearchSource | 72.7% | — | Not comparable |
| τ²-bench resultsSource | 95.9% | 45.3% | Kimi K2.5 leads |
| APEX-Agents-AASource | 11.5% | — | Not comparable |
| Gert LabsSource | 45.88% | — | Not comparable |
| ResearchClawBenchSource | 14.0% | — | Not comparable |
| JobBenchSource | 8.7% | — | Not comparable |
| AA Agentic IndexSource | 21.7% | — | Not comparable |
| GDPval-AASource | 25.1% | 0.0% | Kimi K2.5 leads |
| GDPval-AASource | 1003 | 465 | Kimi K2.5 leads |
| OSWorldSource | — | 47.4% | Not comparable |
CodingKimi K2.5 wins10 benchmarks
| Benchmark | Kimi K2.5 | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 76.8% | — | Not comparable |
| SWE-bench Verified*Source | 70.8% | — | Not comparable |
| LiveCodeBench v6Source | 85.0% | — | Not comparable |
| SWE-bench ProSource | 50.7% | — | Not comparable |
| SWE MultilingualSource | 73% | — | Not comparable |
| SWE-RebenchSource | 58.5% | — | Not comparable |
| React Native EvalsSource | 77.2% | — | Not comparable |
| SciCodeSource | 48.7% | 32% | Kimi K2.5 leads |
| AA-SciCodeSource | 49.0% | 27.8% | Kimi K2.5 leads |
| AA Coding IndexSource | 46.8% | 13.8% | Kimi K2.5 leads |
Reasoning3 benchmarks
KnowledgeNemotron 3 Nano Omni 30B A3B wins12 benchmarks
| Benchmark | Kimi K2.5 | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| GPQASource | 87.6% | 72.2% | Kimi K2.5 leads |
| GPQA-DSource | 87.6% | 72.2% | Kimi K2.5 leads |
| SuperGPQASource | 69.2% | — | Not comparable |
| MMLU-ProSource | 87.1% | 77.3% | Kimi K2.5 leads |
| MMLU-Pro (Arcee)Source | 87.1% | — | Not comparable |
| HLESource | 30.1% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 35.4% | 14.9% | Kimi K2.5 leads |
| AA-GPQA DiamondSource | 87.9% | 46.9% | Kimi K2.5 leads |
| AA-HLESource | 29.4% | 5.3% | Kimi K2.5 leads |
| AA-Omniscience IndexSource | -8.1% | -56.0% | Kimi K2.5 leads |
| AA-Omniscience AccuracySource | 34.3% | 14.8% | Kimi K2.5 leads |
| AA-Omniscience Hallucination RateSource | 64.6% | 83.1% | Kimi K2.5 leads |
Math9 benchmarks
| Benchmark | Kimi K2.5 | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| AIME 2025Source | 96.1% | 82.1% | Kimi K2.5 leads |
| AIME26Source | 95.8% | — | Not comparable |
| AIME25 (Arcee)Source | 96.3% | — | Not comparable |
| HMMT Feb 2025Source | 95.4% | — | Not comparable |
| HMMT Nov 2025Source | 91.1% | — | Not comparable |
| HMMT Feb 2026Source | 87.1% | — | Not comparable |
| MMAnswerBenchSource | 81.8% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 27.900% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 4.200% | — | Not comparable |
Multilingual2 benchmarks
MultimodalKimi K2.5 wins13 benchmarks
| Benchmark | Kimi K2.5 | Nemotron 3 Nano Omni 30B A3B | Result |
|---|---|---|---|
| MMMU-ProSource | 78.5% | — | Not comparable |
| Video-MMESource | 87.4% | — | Not comparable |
| MMVUSource | 80.4% | — | Not comparable |
| VideoMMMUSource | 86.6% | — | Not comparable |
| AA-MMMU-ProSource | 75.4% | 53.2% | Kimi K2.5 leads |
| Design Arena WebsiteSource | 1275 | — | Not comparable |
| MMMUSource | — | 70.8% | Not comparable |
| MMLongBench-DocSource | — | 57.5% | Not comparable |
| CharXivSource | — | 76.3% | Not comparable |
| ScreenSpot ProSource | — | 57.8% | Not comparable |
| Video-MME (w/o subtitle)Source | — | 72.2% | Not comparable |
| AI2D_TESTSource | — | 88.5% | Not comparable |
| RefCOCO (avg)Source | — | 90.5% | Not comparable |
Frequently Asked Questions (5)
Which is better, Kimi K2.5 or Nemotron 3 Nano Omni 30B A3B?
Kimi K2.5 is ahead on BenchLM's BenchAlign leaderboard, 58.78 to 43.32. The biggest single separator in this matchup is SciCode, where the scores are 48.7% and 32%.
Which is better for knowledge tasks, Kimi K2.5 or Nemotron 3 Nano Omni 30B A3B?
Nemotron 3 Nano Omni 30B A3B has the edge for knowledge tasks in this comparison, averaging 76.3 versus 56.9. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
Which is better for coding, Kimi K2.5 or Nemotron 3 Nano Omni 30B A3B?
Kimi K2.5 has the edge for coding in this comparison, averaging 59.4 versus 32. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, Kimi K2.5 or Nemotron 3 Nano Omni 30B A3B?
Kimi K2.5 has the edge for multimodal and grounded tasks in this comparison, averaging 78.5 versus 76.3. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.
Which is better for instruction following, Kimi K2.5 or Nemotron 3 Nano Omni 30B A3B?
Kimi K2.5 has the edge for instruction following in this comparison, averaging 93.9 versus 74.2. Inside this category, AA-IFBench is the benchmark that creates the most daylight between them.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
One email each week. Unsubscribe anytime.