Model comparison
GLM-5.1 vs Nemotron 3 Ultra
Head-to-head evidence from 22 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: GLM-5.1 #12; Nemotron 3 Ultra #24
BenchAlign evidence: GLM-5.1 supported; Nemotron 3 Ultra not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-5.1 and Nemotron 3 Ultra share 22 comparable benchmark results. 3 of 8 categories are comparable. 15 results are unique to GLM-5.1; 17 to Nemotron 3 Ultra.
Updated July 16, 2026- Shared results
- 22
- GLM-5.1 only
- 15
- Nemotron 3 Ultra only
- 17
- Comparable categories
- 3 / 8
Pick GLM-5.1 if you want the stronger benchmark profile. Nemotron 3 Ultra 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 22 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
GLM-5.1 is clearly ahead on the provisional aggregate, 67 to 60. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GLM-5.1's sharpest advantage is in agentic, where it averages 65.4 against 51.3. The single biggest benchmark swing on the page is HLE, 52.3% 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.
GLM-5.1 is also the more expensive model on tokens at $1.40 input / $4.40 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 gives you the larger context window at 1M, compared with 203K for GLM-5.1.
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 | GLM-5.1 | Δ | Nemotron 3 Ultra |
|---|---|---|---|
| Agentic | GLM-5.165.4 | Margin← 14.1 | Nemotron 3 Ultra51.3 |
| Coding | GLM-5.161.3 | Margin← 3.0 | Nemotron 3 Ultra58.3 |
| Knowledge | GLM-5.152.3 | Margin→ 1.9 | Nemotron 3 Ultra54.2 |
| Reasoning | GLM-5.1Not measured | MarginNo overlap | Nemotron 3 Ultra61.9 |
| Math | GLM-5.162.0 | MarginNo overlap | Nemotron 3 UltraNot measured |
| Multilingual | GLM-5.1Not measured | MarginNo overlap | Nemotron 3 Ultra83.0 |
| Inst. Following | GLM-5.1Not 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 52.3%B 26.7%Winner: GLM-5.1Δ 25.6HLE: GLM-5.1 scored 52.3%; Nemotron 3 Ultra scored 26.7%. GLM-5.1 wins this benchmark. - Source ↗
BrowseComp
AgenticA 68%B 44.4%Winner: GLM-5.1Δ 23.6BrowseComp: GLM-5.1 scored 68%; Nemotron 3 Ultra scored 44.4%. GLM-5.1 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 63.5%B 56.4%Winner: GLM-5.1Δ 7.1Terminal-Bench 2.0: GLM-5.1 scored 63.5%; Nemotron 3 Ultra scored 56.4%. GLM-5.1 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-5.1 | Nemotron 3 Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-5.1$1.4 input / $4.4 output | Nemotron 3 Ultra$0 input / $0 output | Nemotron 3 Ultra has the lower combined listed price. |
| Generation speedtokens per second | GLM-5.1Not available | Nemotron 3 UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GLM-5.1Not available | Nemotron 3 UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GLM-5.1203K | Nemotron 3 Ultra1M | Nemotron 3 Ultra lists the larger context window. |
Benchmark Deep Dive
AgenticGLM-5.1 wins17 benchmarks
| Benchmark | GLM-5.1 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 63.5% | 56.4% | GLM-5.1 leads |
| BrowseCompSource | 68% | 44.4% | GLM-5.1 leads |
| τ³-bench resultsSource | 70.6% | 70.9% | Nemotron 3 Ultra leads |
| MCP AtlasSource | 71.8% | — | Not comparable |
| CyberGymSource | 68.7% | — | Not comparable |
| Claw-EvalSource | 62.3% | — | Not comparable |
| AA Agentic IndexSource | 29.9% | 27.4% | GLM-5.1 leads |
| τ²-bench resultsSource | 97.7% | 83.3% | GLM-5.1 leads |
| GDPval-AASource | 37.8% | 33.2% | GLM-5.1 leads |
| Gert LabsSource | 60.11% | — | Not comparable |
| GDPval-AASource | 1257 | 1164 | GLM-5.1 leads |
| ResearchClawBenchSource | 18.2% | — | Not comparable |
| PinchBenchSource | — | 90.0% | 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 |
CodingGLM-5.1 wins12 benchmarks
| Benchmark | GLM-5.1 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| SWE-bench ProSource | 58.4% | — | Not comparable |
| NL2RepoSource | 42.7% | — | Not comparable |
| SWE-RebenchSource | 62.7% | — | Not comparable |
| Vibe Code BenchSource | 31.46% | — | Not comparable |
| AA Coding IndexSource | 55.8% | 49.3% | GLM-5.1 leads |
| Terminal-Bench HardSource | 43.2% | 36.4% | GLM-5.1 leads |
| AA-SciCodeSource | 43.8% | 39.9% | GLM-5.1 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 | GLM-5.1 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| GPQA-DSource | 86.2% | 87.0% | Nemotron 3 Ultra leads |
| HLESource | 52.3% | 26.7% | GLM-5.1 leads |
| Artificial Analysis Intelligence IndexSource | 40.2% | 37.8% | GLM-5.1 leads |
| AA-GPQA DiamondSource | 86.8% | 86.7% | GLM-5.1 leads |
| AA-HLESource | 28.0% | 26.6% | GLM-5.1 leads |
| AA-Omniscience IndexSource | 1.9% | -0.8% | GLM-5.1 leads |
| AA-Omniscience AccuracySource | 24.2% | 21.6% | GLM-5.1 leads |
| AA-Omniscience Hallucination RateSource | 29.4% | 28.5% | Nemotron 3 Ultra leads |
| GPQASource | — | 87% | Not comparable |
| HLE w/o toolsSource | — | 26.7% | Not comparable |
| MMLU-ProSource | — | 86.8% | Not comparable |
| AA Openness IndexSource | — | 83.3% | Not comparable |
Math6 benchmarks
| Benchmark | GLM-5.1 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| AIME26Source | 95.3% | — | Not comparable |
| HMMT Nov 2025Source | 94.0% | — | Not comparable |
| HMMT Feb 2026Source | 82.6% | — | Not comparable |
| MMAnswerBenchSource | 83.8% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 33.448% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 12.500% | — | Not comparable |
Multilingual1 benchmarks
| Benchmark | GLM-5.1 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| MMLU-ProXSource | — | 83% | Not comparable |
Multimodal1 benchmarks
| Benchmark | GLM-5.1 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1312 | 1132 | GLM-5.1 leads |
Frequently Asked Questions (4)
Which is better, GLM-5.1 or Nemotron 3 Ultra?
GLM-5.1 is ahead on BenchLM's provisional leaderboard, 67 to 60. The biggest single separator in this matchup is HLE, where the scores are 52.3% and 26.7%.
Which is better for knowledge tasks, GLM-5.1 or Nemotron 3 Ultra?
Nemotron 3 Ultra has the edge for knowledge tasks in this comparison, averaging 54.2 versus 52.3. Inside this category, HLE is the benchmark that creates the most daylight between them.
Which is better for coding, GLM-5.1 or Nemotron 3 Ultra?
GLM-5.1 has the edge for coding in this comparison, averaging 61.3 versus 58.3. Inside this category, Terminal-Bench Hard is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GLM-5.1 or Nemotron 3 Ultra?
GLM-5.1 has the edge for agentic tasks in this comparison, averaging 65.4 versus 51.3. Inside this category, GDPval-AA 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.