Model comparison
MiMo-V2.5-Pro vs Nemotron 3 Ultra
Head-to-head evidence from 24 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: MiMo-V2.5-Pro unranked; Nemotron 3 Ultra #24
BenchAlign evidence: MiMo-V2.5-Pro supported; Nemotron 3 Ultra not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. MiMo-V2.5-Pro and Nemotron 3 Ultra share 24 comparable benchmark results. 3 of 8 categories are comparable. 6 results are unique to MiMo-V2.5-Pro; 15 to Nemotron 3 Ultra.
Updated July 16, 2026- Shared results
- 24
- MiMo-V2.5-Pro only
- 6
- Nemotron 3 Ultra only
- 15
- Comparable categories
- 3 / 8
Pick MiMo-V2.5-Pro if you want the stronger benchmark profile. Nemotron 3 Ultra only becomes the better choice if knowledge is the priority.
Confidence note. This is a partial-evidence comparison with 24 shared benchmark results across 6 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
MiMo-V2.5-Pro is clearly ahead on the provisional aggregate, 73 to 60. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
MiMo-V2.5-Pro's sharpest advantage is in agentic, where it averages 68.4 against 51.3. The single biggest benchmark swing on the page is HLE, 48% to 26.7%. Nemotron 3 Ultra does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
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 | MiMo-V2.5-Pro | Δ | Nemotron 3 Ultra |
|---|---|---|---|
| Agentic | MiMo-V2.5-Pro68.4 | Margin← 17.1 | Nemotron 3 Ultra51.3 |
| Knowledge | MiMo-V2.5-Pro48.0 | Margin→ 6.2 | Nemotron 3 Ultra54.2 |
| Coding | MiMo-V2.5-Pro57.2 | Margin→ 1.1 | Nemotron 3 Ultra58.3 |
| Reasoning | MiMo-V2.5-ProNot measured | MarginNo overlap | Nemotron 3 Ultra61.9 |
| Multilingual | MiMo-V2.5-ProNot measured | MarginNo overlap | Nemotron 3 Ultra83.0 |
| Inst. Following | MiMo-V2.5-ProNot measured | MarginNo overlap | Nemotron 3 Ultra81.7 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
HLE
KnowledgeA 48%B 26.7%Winner: MiMo-V2.5-ProΔ 21.3HLE: MiMo-V2.5-Pro scored 48%; Nemotron 3 Ultra scored 26.7%. MiMo-V2.5-Pro wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 68.4%B 56.4%Winner: MiMo-V2.5-ProΔ 12Terminal-Bench 2.0: MiMo-V2.5-Pro scored 68.4%; Nemotron 3 Ultra scored 56.4%. MiMo-V2.5-Pro wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | MiMo-V2.5-Pro | Nemotron 3 Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | MiMo-V2.5-ProNot available | Nemotron 3 Ultra$0 input / $0 output | A complete price comparison is not available. |
| Generation speedtokens per second | MiMo-V2.5-ProNot available | Nemotron 3 UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | MiMo-V2.5-ProNot available | Nemotron 3 UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | MiMo-V2.5-Pro1M | Nemotron 3 Ultra1M | Listed context windows are equal. |
Benchmark Deep Dive
AgenticMiMo-V2.5-Pro wins16 benchmarks
| Benchmark | MiMo-V2.5-Pro | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Claw-EvalSource | 63.8% | — | Not comparable |
| GDPval-AASource | 1265 | 1164 | MiMo-V2.5-Pro leads |
| τ³-bench resultsSource | 72.9% | 70.9% | MiMo-V2.5-Pro leads |
| Terminal-Bench 2.0Source | 68.4% | 56.4% | MiMo-V2.5-Pro leads |
| AA Agentic IndexSource | 29.1% | 27.4% | MiMo-V2.5-Pro leads |
| τ²-bench resultsSource | 94.2% | 83.3% | MiMo-V2.5-Pro leads |
| GDPval-AASource | 38.3% | 33.2% | MiMo-V2.5-Pro leads |
| APEX-Agents-AASource | 2.4% | — | Not comparable |
| Gert LabsSource | 62.70% | — | Not comparable |
| AA BriefcaseSource | 873 | 870 | MiMo-V2.5-Pro leads |
| AA ITBenchSource | 38.2% | — | Not comparable |
| PinchBenchSource | — | 90.0% | Not comparable |
| BrowseCompSource | — | 44.4% | Not comparable |
| HLE w/ toolsSource | — | 37.4% | Not comparable |
| AA EnterpriseOps-GymSource | — | 28.9% | Not comparable |
| AA Harvey LABSource | — | 3.3% | Not comparable |
CodingNemotron 3 Ultra wins10 benchmarks
| Benchmark | MiMo-V2.5-Pro | Nemotron 3 Ultra | Result |
|---|---|---|---|
| SWE-bench ProSource | 57.2% | — | Not comparable |
| Terminal-Bench 2.0Source | 68.4% | 56.4% | MiMo-V2.5-Pro leads |
| AA Coding IndexSource | 60.2% | 49.3% | MiMo-V2.5-Pro leads |
| Terminal-Bench HardSource | 43.2% | 36.4% | MiMo-V2.5-Pro leads |
| AA-SciCodeSource | 50.2% | 39.9% | MiMo-V2.5-Pro leads |
| AA Terminal-Bench 2.1Source | 65.2% | — | Not comparable |
| SWE-bench VerifiedSource | — | 71.9% | Not comparable |
| SWE MultilingualSource | — | 67.7% | Not comparable |
| LiveCodeBench v6Source | — | 89.0% | Not comparable |
| SciCodeSource | — | 44.6% | Not comparable |
Reasoning3 benchmarks
KnowledgeNemotron 3 Ultra wins12 benchmarks
| Benchmark | MiMo-V2.5-Pro | Nemotron 3 Ultra | Result |
|---|---|---|---|
| HLESource | 48% | 26.7% | MiMo-V2.5-Pro leads |
| HLE w/o toolsSource | 34% | 26.7% | MiMo-V2.5-Pro leads |
| Artificial Analysis Intelligence IndexSource | 42.2% | 37.8% | MiMo-V2.5-Pro leads |
| AA-GPQA DiamondSource | 86.6% | 86.7% | Nemotron 3 Ultra leads |
| AA-HLESource | 33.8% | 26.6% | MiMo-V2.5-Pro leads |
| AA-Omniscience IndexSource | 3.6% | -0.8% | MiMo-V2.5-Pro leads |
| AA-Omniscience AccuracySource | 22.6% | 21.6% | MiMo-V2.5-Pro leads |
| AA-Omniscience Hallucination RateSource | 24.5% | 28.5% | MiMo-V2.5-Pro leads |
| AA Openness IndexSource | 38.9% | 83.3% | Nemotron 3 Ultra leads |
| GPQASource | — | 87% | Not comparable |
| GPQA-DSource | — | 87.0% | Not comparable |
| MMLU-ProSource | — | 86.8% | Not comparable |
Multilingual1 benchmarks
| Benchmark | MiMo-V2.5-Pro | Nemotron 3 Ultra | Result |
|---|---|---|---|
| MMLU-ProXSource | — | 83% | Not comparable |
Multimodal1 benchmarks
| Benchmark | MiMo-V2.5-Pro | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1302 | 1132 | MiMo-V2.5-Pro leads |
Frequently Asked Questions (4)
Which is better, MiMo-V2.5-Pro or Nemotron 3 Ultra?
MiMo-V2.5-Pro is ahead on BenchLM's provisional leaderboard, 73 to 60. The biggest single separator in this matchup is HLE, where the scores are 48% and 26.7%.
Which is better for knowledge tasks, MiMo-V2.5-Pro or Nemotron 3 Ultra?
Nemotron 3 Ultra has the edge for knowledge tasks in this comparison, averaging 54.2 versus 48. Inside this category, AA Openness Index is the benchmark that creates the most daylight between them.
Which is better for coding, MiMo-V2.5-Pro or Nemotron 3 Ultra?
Nemotron 3 Ultra has the edge for coding in this comparison, averaging 58.3 versus 57.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, MiMo-V2.5-Pro or Nemotron 3 Ultra?
MiMo-V2.5-Pro has the edge for agentic tasks in this comparison, averaging 68.4 versus 51.3. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.