Model comparison
GLM-5 vs Nemotron 3 Ultra
Head-to-head evidence from 23 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: GLM-5 #15; Nemotron 3 Ultra #24
BenchAlign evidence: GLM-5 supported; Nemotron 3 Ultra not scored. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-5 and Nemotron 3 Ultra share 23 comparable benchmark results. 6 of 8 categories are comparable. 27 results are unique to GLM-5; 16 to Nemotron 3 Ultra.
Updated July 16, 2026- Shared results
- 23
- GLM-5 only
- 27
- Nemotron 3 Ultra only
- 16
- Comparable categories
- 6 / 8
Pick GLM-5 if you want the stronger benchmark profile. Nemotron 3 Ultra only becomes the better choice if reasoning is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 23 shared benchmark results across 7 evidence categories; 6 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 has the cleaner provisional overall profile here, landing at 63 versus 60. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
GLM-5's sharpest advantage is in knowledge, where it averages 66.6 against 54.2. The single biggest benchmark swing on the page is HLE, 50.4% to 26.7%. Nemotron 3 Ultra does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.
GLM-5 is also the more expensive model on tokens at $1.00 input / $3.20 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 GLM-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. Nemotron 3 Ultra gives you the larger context window at 1M, compared with 200K for GLM-5.
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 | Δ | Nemotron 3 Ultra |
|---|---|---|---|
| Knowledge | GLM-566.6 | Margin← 12.4 | Nemotron 3 Ultra54.2 |
| Inst. Following | GLM-592.6 | Margin← 10.9 | Nemotron 3 Ultra81.7 |
| Coding | GLM-566.3 | Margin← 8.0 | Nemotron 3 Ultra58.3 |
| Agentic | GLM-556.2 | Margin← 4.9 | Nemotron 3 Ultra51.3 |
| Reasoning | GLM-560.8 | Margin→ 1.1 | Nemotron 3 Ultra61.9 |
| Multilingual | GLM-583.1 | Margin← 0.1 | Nemotron 3 Ultra83.0 |
| Math | GLM-556.3 | MarginNo overlap | Nemotron 3 UltraNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
HLE
KnowledgeA 50.4%B 26.7%Winner: GLM-5Δ 23.7HLE: GLM-5 scored 50.4%; Nemotron 3 Ultra scored 26.7%. GLM-5 wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 77.8%B 71.9%Winner: GLM-5Δ 5.9SWE-bench Verified: GLM-5 scored 77.8%; Nemotron 3 Ultra scored 71.9%. GLM-5 wins this benchmark. - Source ↗
LongBench v2
ReasoningA 60.8%B 61.9%Winner: Nemotron 3 UltraΔ 1.1LongBench v2: GLM-5 scored 60.8%; Nemotron 3 Ultra scored 61.9%. Nemotron 3 Ultra wins this benchmark. - Source ↗
MMLU-Pro
KnowledgeA 85.7%B 86.8%Winner: Nemotron 3 UltraΔ 1.1MMLU-Pro: GLM-5 scored 85.7%; Nemotron 3 Ultra scored 86.8%. Nemotron 3 Ultra wins this benchmark. - Source ↗
GPQA
KnowledgeA 86%B 87%Winner: Nemotron 3 UltraΔ 1GPQA: GLM-5 scored 86%; Nemotron 3 Ultra scored 87%. Nemotron 3 Ultra wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-5 | Nemotron 3 Ultra | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-5$1 input / $3.2 output | Nemotron 3 Ultra$0 input / $0 output | Nemotron 3 Ultra has the lower combined listed price. |
| Generation speedtokens per second | GLM-574 tok/s | Nemotron 3 UltraNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GLM-51.64 s | Nemotron 3 UltraNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GLM-5200K | Nemotron 3 Ultra1M | Nemotron 3 Ultra lists the larger context window. |
Benchmark Deep Dive
AgenticGLM-5 wins22 benchmarks
| Benchmark | GLM-5 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 56.2% | 56.4% | Nemotron 3 Ultra leads |
| Claw-EvalSource | 57.7% | — | Not comparable |
| QwenClawBenchSource | 54.1% | — | Not comparable |
| τ³-bench resultsSource | 65.6% | 70.9% | Nemotron 3 Ultra leads |
| DeepPlanningSource | 14.6% | — | Not comparable |
| ToolathlonSource | 38% | — | Not comparable |
| MCP AtlasSource | 31.1% | — | Not comparable |
| MCP-TasksSource | 60.8% | — | Not comparable |
| WideResearchSource | 69.8% | — | Not comparable |
| τ²-bench resultsSource | 98.2% | 83.3% | GLM-5 leads |
| CyberGymSource | 43.2% | — | Not comparable |
| APEX-Agents-AASource | 14.5% | — | Not comparable |
| Gert LabsSource | 50.99% | — | Not comparable |
| PinchBenchSource | — | 90.0% | Not comparable |
| BrowseCompSource | — | 44.4% | Not comparable |
| GDPval-AASource | — | 33.2% | Not comparable |
| HLE w/ toolsSource | — | 37.4% | Not comparable |
| AA Agentic IndexSource | — | 27.4% | Not comparable |
| GDPval-AASource | — | 1164 | Not comparable |
| AA BriefcaseSource | — | 870 | Not comparable |
| AA EnterpriseOps-GymSource | — | 28.9% | Not comparable |
| AA Harvey LABSource | — | 3.3% | Not comparable |
CodingGLM-5 wins12 benchmarks
| Benchmark | GLM-5 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 77.8% | 71.9% | GLM-5 leads |
| SWE-bench Verified*Source | 72.8% | — | Not comparable |
| SWE-bench ProSource | 55.1% | — | Not comparable |
| SWE MultilingualSource | 73.3% | 67.7% | GLM-5 leads |
| SWE-RebenchSource | 62.8% | — | Not comparable |
| React Native EvalsSource | 74.8% | — | Not comparable |
| Terminal-Bench HardSource | 43.2% | 36.4% | GLM-5 leads |
| AA-SciCodeSource | 46.2% | 39.9% | GLM-5 leads |
| LiveCodeBench v6Source | — | 89.0% | Not comparable |
| SciCodeSource | — | 44.6% | Not comparable |
| Terminal-Bench 2.0Source | — | 56.4% | Not comparable |
| AA Coding IndexSource | — | 49.3% | Not comparable |
ReasoningNemotron 3 Ultra wins4 benchmarks
KnowledgeGLM-5 wins14 benchmarks
| Benchmark | GLM-5 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| GPQASource | 86% | 87% | Nemotron 3 Ultra leads |
| GPQA-DSource | 86.0% | 87.0% | Nemotron 3 Ultra leads |
| SuperGPQASource | 66.8% | — | Not comparable |
| MMLU-ProSource | 85.7% | 86.8% | Nemotron 3 Ultra leads |
| MMLU-Pro (Arcee)Source | 85.8% | — | Not comparable |
| HLESource | 50.4% | 26.7% | GLM-5 leads |
| Artificial Analysis Intelligence IndexSource | 39.5% | 37.8% | GLM-5 leads |
| AA-GPQA DiamondSource | 82.0% | 86.7% | Nemotron 3 Ultra leads |
| AA-HLESource | 27.2% | 26.6% | GLM-5 leads |
| AA-Omniscience IndexSource | 2.0% | -0.8% | GLM-5 leads |
| AA-Omniscience AccuracySource | 26.9% | 21.6% | GLM-5 leads |
| AA-Omniscience Hallucination RateSource | 34.0% | 28.5% | Nemotron 3 Ultra leads |
| HLE w/o toolsSource | — | 26.7% | Not comparable |
| AA Openness IndexSource | — | 83.3% | Not comparable |
Math8 benchmarks
| Benchmark | GLM-5 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| AIME26Source | 95.8% | — | Not comparable |
| AIME25 (Arcee)Source | 93.3% | — | Not comparable |
| HMMT Feb 2025Source | 97.5% | — | Not comparable |
| HMMT Nov 2025Source | 96.9% | — | Not comparable |
| HMMT Feb 2026Source | 86.4% | — | Not comparable |
| MMAnswerBenchSource | 82.5% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 16.434% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 2.100% | — | Not comparable |
MultilingualGLM-5 wins2 benchmarks
Multimodal1 benchmarks
| Benchmark | GLM-5 | Nemotron 3 Ultra | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1282 | 1132 | GLM-5 leads |
Frequently Asked Questions (7)
Which is better, GLM-5 or Nemotron 3 Ultra?
GLM-5 is ahead on BenchLM's provisional leaderboard, 63 to 60. The biggest single separator in this matchup is HLE, where the scores are 50.4% and 26.7%.
Which is better for knowledge tasks, GLM-5 or Nemotron 3 Ultra?
GLM-5 has the edge for knowledge tasks in this comparison, averaging 66.6 versus 54.2. Inside this category, HLE is the benchmark that creates the most daylight between them.
Which is better for coding, GLM-5 or Nemotron 3 Ultra?
GLM-5 has the edge for coding in this comparison, averaging 66.3 versus 58.3. Inside this category, Terminal-Bench Hard is the benchmark that creates the most daylight between them.
Which is better for reasoning, GLM-5 or Nemotron 3 Ultra?
Nemotron 3 Ultra has the edge for reasoning in this comparison, averaging 61.9 versus 60.8. Inside this category, AA-LCR is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GLM-5 or Nemotron 3 Ultra?
GLM-5 has the edge for agentic tasks in this comparison, averaging 56.2 versus 51.3. Inside this category, τ²-bench results is the benchmark that creates the most daylight between them.
Which is better for instruction following, GLM-5 or Nemotron 3 Ultra?
GLM-5 has the edge for instruction following in this comparison, averaging 92.6 versus 81.7. Inside this category, AA-IFBench is the benchmark that creates the most daylight between them.
Which is better for multilingual tasks, GLM-5 or Nemotron 3 Ultra?
GLM-5 has the edge for multilingual tasks in this comparison, averaging 83.1 versus 83. Inside this category, MMLU-ProX 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.