Model comparison
Gemini 2.5 Flash vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 39.0 on the Noometry Index.
Last verified . 23 shared benchmarks.
Google
NVIDIASummary
- They share 23 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Nemotron 3 Ultra in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 36.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.1% for Gemini 2.5 Flash and 86.7% for Nemotron 3 Ultra.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 39.0 | 44.7 |
| Released | 2025-04-17 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $0.60 |
| Output $ / M tokens | $2.50 | $2.40 |
| Results tracked | 54 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Gemini 2.5 Flash: 35.5 (#210), Nemotron 3 Ultra: 37.7 (#174)
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| WeirdML | 41.9% | 43.5% |
| LMArena Coding | 1424 | 1468 |
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| SciCode | — | 40.3% |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.6 (#67), Nemotron 3 Ultra: —
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Nemotron 3 Ultra leads
Gemini 2.5 Flash: 18.2 (#271), Nemotron 3 Ultra: 30.3 (#78)
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 1.1% | 3.1% |
| LMArena Hard Prompts | 1422 | 1452 |
| DTBench | 76.5% | 90.1% |
| LMCA | 27.5% | 36.9% |
| Epoch Capabilities Index | 143.04 | 146.2 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| ARC-AGI-1 | 33.3% | — |
| Chess Puzzles | — | 12% |
| EnigmaEval | 2.7% | — |
| Mystery Game Puzzles | — | 20% |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 38.1 (#87), Nemotron 3 Ultra: 34.4 (#160)
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.1% | 86.7% |
| LMArena Math | 1415 | 1456 |
| ProofBench | — | 2% |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Nemotron 3 Ultra leads
Gemini 2.5 Flash: 36.1 (#162), Nemotron 3 Ultra: 52.5 (#56)
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1426 | 1472 |
| GPQA Diamond | — | 85.4% |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.2 (#31), Nemotron 3 Ultra: —
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1254 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Nemotron 3 Ultra leads
Gemini 2.5 Flash: 52.5 (#83), Nemotron 3 Ultra: 53.7 (#61)
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1410 | 1427 |
| LMArena Chinese | 1450 | 1498 |
| LMArena French | 1433 | 1475 |
| LMArena German | 1419 | 1471 |
| LMArena Korean | 1385 | 1387 |
| LMArena Russian | 1415 | 1415 |
| LMArena Spanish | 1421 | 1452 |
| LMArena Japanese | 1403 | — |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.9 (#50), Nemotron 3 Ultra: 74.9 (#84)
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1405 | 1417 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#16), Nemotron 3 Ultra: 43.9 (#77)
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1419 | 1437 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Nemotron 3 Ultra leads
Gemini 2.5 Flash: 54.0 (#153), Nemotron 3 Ultra: 66.3 (#35)
| Benchmark | Gemini 2.5 Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1417 | 1444 |
| LMArena Creative Writing | 1400 | 1392 |
| EQ-Bench Creative Writing | 1137 | 1692 |
| LMArena Multi-Turn | 1408 | 1412 |
| Short-Story Creative Writing | 76.5% | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 39.0 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or Nemotron 3 Ultra?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is Gemini 2.5 Flash or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 37.7 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 2.5 Flash and Nemotron 3 Ultra share?
23 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Nemotron 3 Ultra has 29.