Model comparison
Gemma 4 31B vs Nemotron 3 Ultra
Head-to-head evidence from 23 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: Gemma 4 31B unranked; Nemotron 3 Ultra #24
BenchAlign evidence: Gemma 4 31B supported; Nemotron 3 Ultra not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Gemma 4 31B and Nemotron 3 Ultra share 23 comparable benchmark results. 2 of 8 categories are comparable. 7 results are unique to Gemma 4 31B; 16 to Nemotron 3 Ultra.
Updated July 16, 2026- Shared results
- 23
- Gemma 4 31B only
- 7
- Nemotron 3 Ultra only
- 16
- Comparable categories
- 2 / 8
Pick Gemma 4 31B if you want the stronger benchmark profile. Nemotron 3 Ultra only becomes the better choice if coding is the priority or you need the larger 1M context window.
Confidence note. This is a partial-evidence comparison with 23 shared benchmark results across 5 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
Gemma 4 31B has the cleaner provisional overall profile here, landing at 62 versus 60. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Nemotron 3 Ultra gives you the larger context window at 1M, compared with 256K for Gemma 4 31B.
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 | Gemma 4 31B | Δ | Nemotron 3 Ultra |
|---|---|---|---|
| Coding | Gemma 4 31B41.6 | Margin→ 16.7 | Nemotron 3 Ultra58.3 |
| Knowledge | Gemma 4 31B53.3 | Margin→ 0.9 | Nemotron 3 Ultra54.2 |
| Agentic | Gemma 4 31BNot measured | MarginNo overlap | Nemotron 3 Ultra51.3 |
| Reasoning | Gemma 4 31BNot measured | MarginNo overlap | Nemotron 3 Ultra61.9 |
| Multilingual | Gemma 4 31BNot measured | MarginNo overlap | Nemotron 3 Ultra83.0 |
| Multimodal | Gemma 4 31B76.9 | MarginNo overlap | Nemotron 3 UltraNot measured |
| Inst. Following | Gemma 4 31BNot measured | MarginNo overlap | Nemotron 3 Ultra81.7 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
GPQA
KnowledgeA 84.3%B 87%Winner: Nemotron 3 UltraΔ 2.7GPQA: Gemma 4 31B scored 84.3%; Nemotron 3 Ultra scored 87%. Nemotron 3 Ultra wins this benchmark. - Source ↗
MMLU-Pro
KnowledgeA 85.2%B 86.8%Winner: Nemotron 3 UltraΔ 1.6MMLU-Pro: Gemma 4 31B scored 85.2%; Nemotron 3 Ultra scored 86.8%. Nemotron 3 Ultra wins this benchmark. - Source ↗
HLE
KnowledgeA 26.5%B 26.7%Winner: Nemotron 3 UltraΔ 0.2HLE: Gemma 4 31B scored 26.5%; Nemotron 3 Ultra scored 26.7%. Nemotron 3 Ultra wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Gemma 4 31B | Nemotron 3 Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Gemma 4 31B$0 input / $0 output | Nemotron 3 Ultra$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | Gemma 4 31BNot available | Nemotron 3 UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Gemma 4 31BNot available | Nemotron 3 UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Gemma 4 31B256K | Nemotron 3 Ultra1M | Nemotron 3 Ultra lists the larger context window. |
Benchmark Deep Dive
Agentic15 benchmarks
| Benchmark | Gemma 4 31B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| AA Agentic IndexSource | 14.4% | 27.4% | Nemotron 3 Ultra leads |
| τ²-bench resultsSource | 59.9% | 83.3% | Nemotron 3 Ultra leads |
| GDPval-AASource | 15.2% | 33.2% | Nemotron 3 Ultra leads |
| GDPval-AASource | 804 | 1164 | Nemotron 3 Ultra leads |
| Gert LabsSource | 35.26% | — | Not comparable |
| AA EnterpriseOps-GymSource | 28.3% | 28.9% | Nemotron 3 Ultra leads |
| AA Harvey LABSource | 0.0% | 3.3% | Nemotron 3 Ultra leads |
| AA ITBenchSource | 37.3% | — | Not comparable |
| AA Tau3 BankingSource | 15.1% | — | Not comparable |
| Terminal-Bench 2.0Source | — | 56.4% | 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 |
CodingNemotron 3 Ultra wins10 benchmarks
| Benchmark | Gemma 4 31B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| SWE-RebenchSource | 41.6% | — | Not comparable |
| React Native EvalsSource | 75.2% | — | Not comparable |
| AA Coding IndexSource | 43.4% | 49.3% | Nemotron 3 Ultra leads |
| Terminal-Bench HardSource | 36.4% | 36.4% | Tie |
| AA-SciCodeSource | 43.4% | 39.9% | Gemma 4 31B leads |
| SWE-bench VerifiedSource | — | 71.9% | Not comparable |
| SWE MultilingualSource | — | 67.7% | Not comparable |
| LiveCodeBench v6Source | — | 89.0% | Not comparable |
| SciCodeSource | — | 44.6% | Not comparable |
| Terminal-Bench 2.0Source | — | 56.4% | Not comparable |
Reasoning3 benchmarks
KnowledgeNemotron 3 Ultra wins12 benchmarks
| Benchmark | Gemma 4 31B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| GPQASource | 84.3% | 87% | Nemotron 3 Ultra leads |
| MMLU-ProSource | 85.2% | 86.8% | Nemotron 3 Ultra leads |
| HLESource | 26.5% | 26.7% | Nemotron 3 Ultra leads |
| HLE w/o toolsSource | 19.5% | 26.7% | Nemotron 3 Ultra leads |
| Artificial Analysis Intelligence IndexSource | 29.4% | 37.8% | Nemotron 3 Ultra leads |
| AA-GPQA DiamondSource | 85.7% | 86.7% | Nemotron 3 Ultra leads |
| AA-HLESource | 22.7% | 26.6% | Nemotron 3 Ultra leads |
| AA-Omniscience IndexSource | -45.4% | -0.8% | Nemotron 3 Ultra leads |
| AA-Omniscience AccuracySource | 19.9% | 21.6% | Nemotron 3 Ultra leads |
| AA-Omniscience Hallucination RateSource | 81.6% | 28.5% | Nemotron 3 Ultra leads |
| AA Openness IndexSource | 38.9% | 83.3% | Nemotron 3 Ultra leads |
| GPQA-DSource | — | 87.0% | Not comparable |
Multilingual1 benchmarks
| Benchmark | Gemma 4 31B | Nemotron 3 Ultra | Result |
|---|---|---|---|
| MMLU-ProXSource | — | 83% | Not comparable |
Multimodal3 benchmarks
Frequently Asked Questions (3)
Which is better, Gemma 4 31B or Nemotron 3 Ultra?
Gemma 4 31B is ahead on BenchLM's provisional leaderboard, 62 to 60. The biggest single separator in this matchup is GPQA, where the scores are 84.3% and 87%.
Which is better for knowledge tasks, Gemma 4 31B or Nemotron 3 Ultra?
Nemotron 3 Ultra has the edge for knowledge tasks in this comparison, averaging 54.2 versus 53.3. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Which is better for coding, Gemma 4 31B or Nemotron 3 Ultra?
Nemotron 3 Ultra has the edge for coding in this comparison, averaging 58.3 versus 41.6. Inside this category, AA Coding Index 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
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.