Model comparison
DeepSeek V4 Pro vs Gemini 2.0 Flash-Lite
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 37.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeek
GoogleSummary
- They share 19 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Gemini 2.0 Flash-Lite in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 22.0.
- The biggest single-benchmark swing is DTBench: 93.9% for DeepSeek V4 Pro and 52.5% for Gemini 2.0 Flash-Lite.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Gemini 2.0 Flash-Lite | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 54.3 | 37.8 |
| Released | 2026-04-24 | 2025-02-05 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Gemini 2.0 Flash-Lite: 37.9 (#185)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Coding | 1470 | 1322 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| LiveBench Coding | — | 47.1% |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Gemini 2.0 Flash-Lite: —
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Gemini 2.0 Flash-Lite: 22.0 (#210)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1324 |
| DTBench | 93.9% | 52.5% |
| ForecastBench | 56.1 | 57.1 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| LiveBench Reasoning | — | 50.1% |
| Mystery Game Puzzles | 43% | — |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| LiveBench | — | 54.3% |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Gemini 2.0 Flash-Lite: 34.1 (#196)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Math | 1455 | 1309 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 37.4% |
| LiveBench Math | — | 58.1% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Gemini 2.0 Flash-Lite: 35.0 (#189)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Expert | 1464 | 1305 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| MMLU-Pro | — | 72% |
| Vectara Hallucination Rate | 8.6% | — |
| GPQA (HELM) | — | 50% |
Multimodal Not comparable
DeepSeek V4 Pro: —, Gemini 2.0 Flash-Lite: 31.2 (#109)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1100 |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Gemini 2.0 Flash-Lite: 46.0 (#161)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1439 | 1323 |
| LMArena Chinese | 1486 | 1339 |
| LMArena French | 1472 | 1347 |
| LMArena German | 1458 | 1306 |
| LMArena Japanese | 1445 | 1301 |
| LMArena Korean | 1447 | 1325 |
| LMArena Russian | 1453 | 1328 |
| LMArena Spanish | 1458 | 1313 |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Gemini 2.0 Flash-Lite: 70.4 (#163)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Instruction Following | 1448 | 1305 |
| LiveBench Instruction Following | — | 78.3% |
| IFEval | — | 82.4% |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), Gemini 2.0 Flash-Lite: 40.1 (#160)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1458 | 1320 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Gemini 2.0 Flash-Lite: 51.7 (#177)
| Benchmark | DeepSeek V4 Pro | Gemini 2.0 Flash-Lite |
|---|---|---|
| LMArena Text | 1451 | 1330 |
| LMArena Creative Writing | 1446 | 1319 |
| LMArena Multi-Turn | 1467 | 1307 |
| EQ-Bench Creative Writing | 1553 | — |
| WildBench | — | 79% |
| EQ-Bench 4 | 1166 | — |
| LiveBench Language | — | 34.3% |
Frequently asked questions
Is DeepSeek V4 Pro better than Gemini 2.0 Flash-Lite?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 37.8 on the Noometry Index.
Is DeepSeek V4 Pro or Gemini 2.0 Flash-Lite better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 37.9 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Gemini 2.0 Flash-Lite share?
19 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Gemini 2.0 Flash-Lite has 32.