Model comparison
DeepSeek V4 Pro vs Gemini 2.5 Flash-Lite
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 3.1× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
DeepSeek
GoogleSummary
- They share 24 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 9 categories and Gemini 2.5 Flash-Lite in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.4 to 21.5.
- The biggest single-benchmark swing is DTBench: 93.9% for DeepSeek V4 Pro and 62.8% for Gemini 2.5 Flash-Lite.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.43 / $0.87 for DeepSeek V4 Pro.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Gemini 2.5 Flash-Lite | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 54.2 | 36.4 |
| Released | 2026-04-24 | 2025-06-17 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 393K | 66K |
| Input $ / M tokens | $0.43 | $0.10 |
| Output $ / M tokens | $0.87 | $0.40 |
| Results tracked | 48 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.2 (#31), Gemini 2.5 Flash-Lite: 38.0 (#167)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| WeirdML | 66.2% | 35.2% |
| LMArena Coding | 1470 | 1373 |
| ALE-Bench | 1,403 | 325.9 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
Agentic & Tool Use DeepSeek V4 Pro leads
DeepSeek V4 Pro: 32.7 (#54), Gemini 2.5 Flash-Lite: 27.8 (#89)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Berkeley Function Calling Leaderboard | — | 36.9% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.4 (#22), Gemini 2.5 Flash-Lite: 21.5 (#196)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| Kagi LLM Benchmark | 53.5% | 40.5% |
| LMArena Hard Prompts | 1461 | 1377 |
| DTBench | 93.9% | 62.8% |
| LMCA | 45.5% | 18.1% |
| Epoch Capabilities Index | 155.39 | 133.93 |
| ARC-AGI-2 | 61.3% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.6 (#24), Gemini 2.5 Flash-Lite: 35.5 (#144)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Math | 1455 | 1373 |
| 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 | — | 48% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#28), Gemini 2.5 Flash-Lite: 32.1 (#206)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| Vectara Hallucination Rate | 8.6% | 3.3% |
| LMArena Expert | 1463 | 1373 |
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| MMLU-Pro | — | 53.7% |
| GPQA (HELM) | — | 30.9% |
Multimodal Not comparable
DeepSeek V4 Pro: —, Gemini 2.5 Flash-Lite: 28.6 (#109)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1198 |
| VPCT | — | 30% |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.5 (#44), Gemini 2.5 Flash-Lite: 49.5 (#129)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1438 | 1369 |
| LMArena Chinese | 1486 | 1404 |
| LMArena French | 1473 | 1388 |
| LMArena German | 1458 | 1390 |
| LMArena Japanese | 1448 | 1359 |
| LMArena Korean | 1452 | 1358 |
| LMArena Russian | 1452 | 1373 |
| LMArena Spanish | 1457 | 1396 |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.3 (#44), Gemini 2.5 Flash-Lite: 70.2 (#163)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Instruction Following | 1448 | 1366 |
| IFEval | — | 81% |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#49), Gemini 2.5 Flash-Lite: 33.3 (#257)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1459 | 1373 |
| Fiction.LiveBench | — | 47.2% |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.6 (#45), Gemini 2.5 Flash-Lite: 57.0 (#130)
| Benchmark | DeepSeek V4 Pro | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Text | 1451 | 1379 |
| LMArena Creative Writing | 1446 | 1366 |
| LMArena Multi-Turn | 1467 | 1367 |
| EQ-Bench Creative Writing | 1553 | — |
| WildBench | — | 81.8% |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Gemini 2.5 Flash-Lite?
DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 36.4 on the Noometry Index. Gemini 2.5 Flash-Lite costs 3.1× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4 Pro or Gemini 2.5 Flash-Lite?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; DeepSeek V4 Pro lists at $0.43 and $0.87.
Is DeepSeek V4 Pro or Gemini 2.5 Flash-Lite better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 38.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 1M.
How many benchmarks do DeepSeek V4 Pro and Gemini 2.5 Flash-Lite share?
24 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.