Model comparison
DeepSeek-V2.5 (Sep 2024) vs Gemini 4 Argon
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 37.6 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
GoogleSummary
- They share 13 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Gemini 4 Argon in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 4 Argon leads 73.9 to 35.9.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 56.5 |
| Released | 2024-09-06 | 2026-09-30 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 4 Argon leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Gemini 4 Argon: 62.0 (#9)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| LMArena Coding | 1309 | 1550 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1678 |
| FrontierSWE | — | 55% |
| SciCode | — | 61.8% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemini 4 Argon: 49.2 (#8)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | — | 82.2% |
| Vending-Bench 2 | — | 13,718 |
Reasoning Gemini 4 Argon leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Gemini 4 Argon: 44.2 (#47)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1548 |
| CritPt | — | 27.1% |
Math Gemini 4 Argon leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Gemini 4 Argon: 73.9 (#17)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| LMArena Math | 1288 | 1536 |
| ProofBench | — | 99% |
Knowledge Gemini 4 Argon leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Gemini 4 Argon: 43.9 (#89)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1266 | 1553 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemini 4 Argon: 46.5 (#14)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| Blueprint-Bench 2 | — | 54.4% |
Multilingual Gemini 4 Argon leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Gemini 4 Argon: 60.3 (#1)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1273 | 1523 |
| LMArena Chinese | 1318 | 1610 |
| LMArena Russian | 1289 | 1537 |
| LMArena Spanish | 1248 | 1497 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
Instruction Following Gemini 4 Argon leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Gemini 4 Argon: 80.1 (#2)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1280 | 1538 |
Long Context Gemini 4 Argon leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Gemini 4 Argon: 47.6 (#15)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1301 | 1549 |
Writing & Preference Gemini 4 Argon leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Gemini 4 Argon: 71.4 (#19)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1294 | 1534 |
| LMArena Creative Writing | 1285 | 1531 |
| LMArena Multi-Turn | 1297 | 1557 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Gemini 4 Argon?
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Gemini 4 Argon better for coding?
Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemini 4 Argon share?
13 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemini 4 Argon has 21.