Model comparison
Gemini 2.5 Flash-Lite vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 36.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 3 categories and Nemotron 3 Super in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where Nemotron 3 Super leads 41.5 to 33.3.
- Both cost about the same: $0.10 input and $0.40 output per million tokens.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 262K.
- Nemotron 3 Super has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | Nemotron 3 Super | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 36.4 | 39.6 |
| Released | 2025-06-17 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.10 | $0.08 |
| Output $ / M tokens | $0.40 | $0.45 |
| Results tracked | 33 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 2.5 Flash-Lite: 38.0 (#167), Nemotron 3 Super: 38.9 (#153)
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| WeirdML | 35.2% | 38% |
| LMArena Coding | 1373 | 1403 |
| ALE-Bench | 325.9 | 213.9 |
| SciCode | — | 36% |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash-Lite: 27.8 (#89), Nemotron 3 Super: —
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | — |
Reasoning Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 21.5 (#196), Nemotron 3 Super: 17.9 (#274)
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1377 | 1386 |
| Kagi LLM Benchmark | 40.5% | — |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| DTBench | 62.8% | — |
| LMCA | 18.1% | — |
| Epoch Capabilities Index | 133.93 | — |
Math Nemotron 3 Super leads
Gemini 2.5 Flash-Lite: 35.5 (#144), Nemotron 3 Super: 37.6 (#95)
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1373 | 1381 |
| MathArena Final-Answer Competitions | — | 60.4% |
| Omni-MATH | 48% | — |
Knowledge Nemotron 3 Super leads
Gemini 2.5 Flash-Lite: 32.1 (#206), Nemotron 3 Super: 38.2 (#136)
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1373 | 1397 |
| MMLU-Pro | 53.7% | — |
| Vectara Hallucination Rate | 3.3% | — |
| GPQA (HELM) | 30.9% | — |
Multimodal Not comparable
Gemini 2.5 Flash-Lite: 28.6 (#109), Nemotron 3 Super: —
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1198 | — |
| VPCT | 30% | — |
Multilingual Too close to call
Gemini 2.5 Flash-Lite: 49.5 (#129), Nemotron 3 Super: 48.6 (#139)
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1369 | 1356 |
| LMArena Chinese | 1404 | 1430 |
| LMArena French | 1388 | 1404 |
| LMArena German | 1390 | 1341 |
| LMArena Russian | 1373 | 1336 |
| LMArena Spanish | 1396 | 1417 |
| LMArena Japanese | 1359 | — |
| LMArena Korean | 1358 | — |
Instruction Following Nemotron 3 Super leads
Gemini 2.5 Flash-Lite: 70.2 (#163), Nemotron 3 Super: 71.4 (#149)
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1366 | 1347 |
| IFEval | 81% | — |
Long Context Nemotron 3 Super leads
Gemini 2.5 Flash-Lite: 33.3 (#257), Nemotron 3 Super: 41.5 (#134)
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1373 | 1362 |
| Fiction.LiveBench | 47.2% | — |
Writing & Preference Too close to call
Gemini 2.5 Flash-Lite: 57.0 (#130), Nemotron 3 Super: 56.1 (#135)
| Benchmark | Gemini 2.5 Flash-Lite | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1379 | 1378 |
| LMArena Creative Writing | 1366 | 1317 |
| LMArena Multi-Turn | 1367 | 1369 |
| WildBench | 81.8% | — |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 36.4 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash-Lite or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Gemini 2.5 Flash-Lite lists at $0.10 and $0.40.
Is Gemini 2.5 Flash-Lite or Nemotron 3 Super better for coding?
They score almost the same on coding (38.0 vs 38.9); test both on your own repository before choosing.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 2.5 Flash-Lite and Nemotron 3 Super share?
17 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Nemotron 3 Super has 21.