Model comparison
Gemini 3 Deep Think vs Nova 2 Lite
Nova 2 Lite has enough public results to be ranked (#161); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
GoogleSummary
- The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 27.5.
Side by side
| Gemini 3 Deep Think | Nova 2 Lite | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 58.3 | 39.7 |
| Released | 2026-02-12 | 2025-12-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 3 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 3 Deep Think: —, Nova 2 Lite: 40.7 (#134)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| LMArena Coding | — | 1385 |
Agentic & Tool Use Not comparable
Gemini 3 Deep Think: —, Nova 2 Lite: 24.1 (#121)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |
Reasoning Gemini 3 Deep Think leads
Gemini 3 Deep Think: 70.2 (#14), Nova 2 Lite: 27.5 (#118)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| ARC-AGI-2 | 84.6% | — |
| ARC-AGI-1 | 96% | — |
| CritPt | 25.7% | — |
| LMArena Hard Prompts | — | 1364 |
Math Not comparable
Gemini 3 Deep Think: —, Nova 2 Lite: 37.5 (#156)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| LMArena Math | — | 1359 |
Knowledge Not comparable
Gemini 3 Deep Think: —, Nova 2 Lite: 43.0 (#94)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1358 |
Multilingual Not comparable
Gemini 3 Deep Think: —, Nova 2 Lite: 47.1 (#153)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| LMArena Non-English | — | 1337 |
| LMArena Chinese | — | 1364 |
| LMArena French | — | 1381 |
| LMArena German | — | 1343 |
| LMArena Japanese | — | 1271 |
| LMArena Korean | — | 1284 |
| LMArena Russian | — | 1343 |
| LMArena Spanish | — | 1373 |
Instruction Following Not comparable
Gemini 3 Deep Think: —, Nova 2 Lite: 70.5 (#161)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| LMArena Instruction Following | — | 1335 |
Long Context Not comparable
Gemini 3 Deep Think: —, Nova 2 Lite: 40.6 (#150)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| LMArena Longer Query | — | 1335 |
Writing & Preference Not comparable
Gemini 3 Deep Think: —, Nova 2 Lite: 53.9 (#154)
| Benchmark | Gemini 3 Deep Think | Nova 2 Lite |
|---|---|---|
| LMArena Text | — | 1362 |
| LMArena Creative Writing | — | 1291 |
| LMArena Multi-Turn | — | 1338 |
Frequently asked questions
Is Gemini 3 Deep Think better than Nova 2 Lite?
Nova 2 Lite has enough public results to be ranked (#161); Gemini 3 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Gemini 3 Deep Think and Nova 2 Lite share?
0 benchmarks have published results for both models. Gemini 3 Deep Think has 3 scored results on Noometry and Nova 2 Lite has 19.