Model comparison
DeepSeek-V3.1-Terminus vs Gemini 2.5 Flash-Lite
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 2.6× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
DeepSeek
GoogleSummary
- They share 14 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Gemini 2.5 Flash-Lite in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where DeepSeek-V3.1-Terminus leads 43.4 to 33.3.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus 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 $0.27 / $1 for DeepSeek-V3.1-Terminus.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 43.1 | 37.0 |
| Released | 2025-09-22 | 2025-06-17 |
| Weights | Open | Proprietary |
| Context window | 164K | 1.05M |
| Max output | 147K | 66K |
| Input $ / M tokens | $0.27 | $0.10 |
| Output $ / M tokens | $1 | $0.40 |
| Results tracked | 16 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Gemini 2.5 Flash-Lite: 38.5 (#173)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Coding | 1426 | 1373 |
| ALE-Bench | 745.17 | 325.9 |
| SciCode | 40.6% | — |
| WeirdML | — | 35.2% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 2.5 Flash-Lite: 28.0 (#96)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 36.9% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Gemini 2.5 Flash-Lite: 22.2 (#205)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 40.5% |
| LMArena Hard Prompts | 1426 | 1377 |
| DTBench | 81.3% | 62.8% |
| LMCA | 28.6% | 18.1% |
| CritPt | 1.7% | — |
| Epoch Capabilities Index | — | 133.94 |
Math Too close to call
DeepSeek-V3.1-Terminus: 38.5 (#137), Gemini 2.5 Flash-Lite: 38.0 (#144)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Math | 1402 | 1373 |
| Omni-MATH | — | 48% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 2.5 Flash-Lite: 32.5 (#210)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| MMLU-Pro | — | 53.7% |
| Vectara Hallucination Rate | — | 3.3% |
| GPQA (HELM) | — | 30.9% |
| LMArena Expert | — | 1373 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Gemini 2.5 Flash-Lite: 29.1 (#114)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1198 |
| VPCT | — | 30% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Gemini 2.5 Flash-Lite: 49.3 (#134)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1407 | 1369 |
| LMArena Russian | 1436 | 1373 |
| LMArena Chinese | — | 1404 |
| LMArena French | — | 1388 |
| LMArena German | — | 1389 |
| LMArena Japanese | — | 1359 |
| LMArena Korean | — | 1360 |
| LMArena Spanish | — | 1396 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Gemini 2.5 Flash-Lite: 70.0 (#168)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Instruction Following | 1404 | 1367 |
| IFEval | — | 81% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Gemini 2.5 Flash-Lite: 33.3 (#262)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1421 | 1373 |
| Fiction.LiveBench | — | 47.2% |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Gemini 2.5 Flash-Lite: 56.8 (#135)
| Benchmark | DeepSeek-V3.1-Terminus | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Text | 1419 | 1379 |
| LMArena Creative Writing | 1403 | 1367 |
| LMArena Multi-Turn | 1411 | 1366 |
| WildBench | — | 81.8% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Gemini 2.5 Flash-Lite?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 2.6× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus 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-V3.1-Terminus lists at $0.27 and $1.
Is DeepSeek-V3.1-Terminus or Gemini 2.5 Flash-Lite better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 38.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 2.5 Flash-Lite share?
14 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.