Model comparison
MiniMax M2.7 vs Nemotron 3 Ultra
Head-to-head evidence from 20 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: MiniMax M2.7 unranked; Nemotron 3 Ultra #24
BenchAlign evidence: MiniMax M2.7 supported; Nemotron 3 Ultra not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. MiniMax M2.7 and Nemotron 3 Ultra share 20 comparable benchmark results. 2 of 8 categories are comparable. 17 results are unique to MiniMax M2.7; 19 to Nemotron 3 Ultra.
Updated July 16, 2026- Shared results
- 20
- MiniMax M2.7 only
- 17
- Nemotron 3 Ultra only
- 19
- Comparable categories
- 2 / 8
Pick Nemotron 3 Ultra if you want the stronger benchmark profile. MiniMax M2.7 only becomes the better choice if agentic is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 20 shared benchmark results across 6 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Nemotron 3 Ultra is clearly ahead on the provisional aggregate, 60 to 52. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Nemotron 3 Ultra's sharpest advantage is in coding, where it averages 58.3 against 53.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 57% to 56.4%. MiniMax M2.7 does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
MiniMax M2.7 is also the more expensive model on tokens at $0.30 input / $1.20 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Nemotron 3 Ultra. That is roughly Infinityx on output cost alone. Nemotron 3 Ultra is the reasoning model in the pair, while MiniMax M2.7 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. Nemotron 3 Ultra gives you the larger context window at 1M, compared with 200K for MiniMax M2.7.
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 | MiniMax M2.7 | Δ | Nemotron 3 Ultra |
|---|---|---|---|
| Agentic | MiniMax M2.757.0 | Margin← 5.7 | Nemotron 3 Ultra51.3 |
| Coding | MiniMax M2.753.3 | Margin→ 5.0 | Nemotron 3 Ultra58.3 |
| Reasoning | MiniMax M2.7Not measured | MarginNo overlap | Nemotron 3 Ultra61.9 |
| Knowledge | MiniMax M2.7Not measured | MarginNo overlap | Nemotron 3 Ultra54.2 |
| Multilingual | MiniMax M2.7Not measured | MarginNo overlap | Nemotron 3 Ultra83.0 |
| Inst. Following | MiniMax M2.7Not measured | MarginNo overlap | Nemotron 3 Ultra81.7 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 57%B 56.4%Winner: MiniMax M2.7Δ 0.6Terminal-Bench 2.0: MiniMax M2.7 scored 57%; Nemotron 3 Ultra scored 56.4%. MiniMax M2.7 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | MiniMax M2.7 | Nemotron 3 Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | MiniMax M2.7$0.3 input / $1.2 output | Nemotron 3 Ultra$0 input / $0 output | Nemotron 3 Ultra has the lower combined listed price. |
| Generation speedtokens per second | MiniMax M2.745 tok/s | Nemotron 3 UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | MiniMax M2.72.53 s | Nemotron 3 UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | MiniMax M2.7200K | Nemotron 3 Ultra1M | Nemotron 3 Ultra lists the larger context window. |
Benchmark Deep Dive
AgenticMiniMax M2.7 wins18 benchmarks
| Benchmark | MiniMax M2.7 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 57% | 56.4% | MiniMax M2.7 leads |
| τ²-bench resultsSource | 84.8% | 83.3% | MiniMax M2.7 leads |
| ToolathlonSource | 46.3% | — | Not comparable |
| MLE-Bench LiteSource | 66.6% | — | Not comparable |
| MM-ClawBenchSource | 62.7% | — | Not comparable |
| Claw-EvalSource | 48.7% | — | Not comparable |
| AA Agentic IndexSource | 25.6% | 27.4% | Nemotron 3 Ultra leads |
| APEX-Agents-AASource | 10.6% | — | Not comparable |
| GDPval-AASource | 32.9% | 33.2% | Nemotron 3 Ultra leads |
| GDPval-AASource | 1158 | 1164 | Nemotron 3 Ultra leads |
| Gert LabsSource | 40.40% | — | Not comparable |
| PinchBenchSource | — | 90.0% | Not comparable |
| BrowseCompSource | — | 44.4% | Not comparable |
| τ³-bench resultsSource | — | 70.9% | Not comparable |
| HLE w/ toolsSource | — | 37.4% | Not comparable |
| AA BriefcaseSource | — | 870 | Not comparable |
| AA EnterpriseOps-GymSource | — | 28.9% | Not comparable |
| AA Harvey LABSource | — | 3.3% | Not comparable |
CodingNemotron 3 Ultra wins16 benchmarks
| Benchmark | MiniMax M2.7 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| SWE-bench Verified*Source | 75.4% | — | Not comparable |
| SWE-bench ProSource | 56.2% | — | Not comparable |
| SWE-RebenchSource | 51.9% | — | Not comparable |
| SWE MultilingualSource | 76.5% | 67.7% | MiniMax M2.7 leads |
| Multi-SWE BenchSource | 52.7% | — | Not comparable |
| VIBE-ProSource | 55.6% | — | Not comparable |
| NL2RepoSource | 39.8% | — | Not comparable |
| Vibe Code BenchSource | 27.04% | — | Not comparable |
| React Native EvalsSource | 71.4% | — | Not comparable |
| AA Coding IndexSource | 52.6% | 49.3% | MiniMax M2.7 leads |
| Terminal-Bench HardSource | 39.4% | 36.4% | MiniMax M2.7 leads |
| AA-SciCodeSource | 47.0% | 39.9% | MiniMax M2.7 leads |
| SWE-bench VerifiedSource | — | 71.9% | Not comparable |
| LiveCodeBench v6Source | — | 89.0% | Not comparable |
| SciCodeSource | — | 44.6% | Not comparable |
| Terminal-Bench 2.0Source | — | 56.4% | Not comparable |
Reasoning3 benchmarks
Knowledge13 benchmarks
| Benchmark | MiniMax M2.7 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| GPQA-DSource | 87.0% | 87.0% | Tie |
| MMLU-Pro (Arcee)Source | 80.8% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 38.1% | 37.8% | MiniMax M2.7 leads |
| AA-GPQA DiamondSource | 87.4% | 86.7% | MiniMax M2.7 leads |
| AA-HLESource | 28.1% | 26.6% | MiniMax M2.7 leads |
| AA-Omniscience IndexSource | 0.7% | -0.8% | MiniMax M2.7 leads |
| AA-Omniscience AccuracySource | 26.1% | 21.6% | MiniMax M2.7 leads |
| AA-Omniscience Hallucination RateSource | 34.4% | 28.5% | Nemotron 3 Ultra leads |
| GPQASource | — | 87% | Not comparable |
| HLESource | — | 26.7% | Not comparable |
| HLE w/o toolsSource | — | 26.7% | Not comparable |
| MMLU-ProSource | — | 86.8% | Not comparable |
| AA Openness IndexSource | — | 83.3% | Not comparable |
Math1 benchmarks
| Benchmark | MiniMax M2.7 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| AIME25 (Arcee)Source | 80.0% | — | Not comparable |
Multilingual1 benchmarks
| Benchmark | MiniMax M2.7 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| MMLU-ProXSource | — | 83% | Not comparable |
Multimodal2 benchmarks
Frequently Asked Questions (3)
Which is better, MiniMax M2.7 or Nemotron 3 Ultra?
Nemotron 3 Ultra is ahead on BenchLM's provisional leaderboard, 60 to 52. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 57% and 56.4%.
Which is better for coding, MiniMax M2.7 or Nemotron 3 Ultra?
Nemotron 3 Ultra has the edge for coding in this comparison, averaging 58.3 versus 53.3. Inside this category, SWE Multilingual is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, MiniMax M2.7 or Nemotron 3 Ultra?
MiniMax M2.7 has the edge for agentic tasks in this comparison, averaging 57 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.