Model comparison
DeepSeek-R1 vs Gemini 4 Argon
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 42.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeek
GoogleSummary
- They share 15 benchmarks with published results for both. DeepSeek-R1 scores higher in 1 category 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 43.8.
- The biggest single-benchmark swing is SciCode: 35.7% for DeepSeek-R1 and 61.8% for Gemini 4 Argon.
Side by side
| DeepSeek-R1 | Gemini 4 Argon | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 42.3 | 56.5 |
| Released | 2025-01-20 | 2026-09-30 |
| Weights | Proprietary | Proprietary |
| Context window | 164K | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $2.15 | — |
| Results tracked | 52 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 4 Argon leads
DeepSeek-R1: 46.3 (#68), Gemini 4 Argon: 62.0 (#9)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| SciCode | 35.7% | 61.8% |
| LMArena Coding | 1427 | 1550 |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1678 |
| FrontierSWE | — | 55% |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Gemini 4 Argon leads
DeepSeek-R1: 30.7 (#75), Gemini 4 Argon: 49.2 (#8)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | — | 82.2% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
| Vending-Bench 2 | — | 13,718 |
Reasoning Gemini 4 Argon leads
DeepSeek-R1: 18.6 (#278), Gemini 4 Argon: 44.2 (#47)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| CritPt | 1.1% | 27.1% |
| LMArena Hard Prompts | 1416 | 1548 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.29 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math Gemini 4 Argon leads
DeepSeek-R1: 43.8 (#79), Gemini 4 Argon: 73.9 (#17)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| LMArena Math | 1400 | 1536 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| ProofBench | — | 99% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge Too close to call
DeepSeek-R1: 44.5 (#87), Gemini 4 Argon: 43.9 (#89)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1394 | 1553 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multimodal Not comparable
DeepSeek-R1: —, Gemini 4 Argon: 46.5 (#14)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| Blueprint-Bench 2 | — | 54.4% |
Multilingual Gemini 4 Argon leads
DeepSeek-R1: 52.4 (#85), Gemini 4 Argon: 60.3 (#1)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1412 | 1523 |
| LMArena Chinese | 1442 | 1610 |
| LMArena Russian | 1423 | 1537 |
| LMArena Spanish | 1411 | 1497 |
| LMArena French | 1417 | — |
| LMArena German | 1404 | — |
| LMArena Japanese | 1391 | — |
| LMArena Korean | 1360 | — |
Instruction Following Gemini 4 Argon leads
DeepSeek-R1: 72.0 (#143), Gemini 4 Argon: 80.1 (#2)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1382 | 1538 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context Gemini 4 Argon leads
DeepSeek-R1: 45.4 (#36), Gemini 4 Argon: 47.6 (#15)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1391 | 1549 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Gemini 4 Argon leads
DeepSeek-R1: 61.4 (#88), Gemini 4 Argon: 71.4 (#19)
| Benchmark | DeepSeek-R1 | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1428 | 1534 |
| LMArena Creative Writing | 1405 | 1531 |
| LMArena Multi-Turn | 1405 | 1557 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Gemini 4 Argon?
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 42.3 on the Noometry Index.
Is DeepSeek-R1 or Gemini 4 Argon better for coding?
Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 46.3 in the Noometry coding category.
How many benchmarks do DeepSeek-R1 and Gemini 4 Argon share?
15 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Gemini 4 Argon has 21.