Model comparison
Gemini 3.1 Pro Preview vs Gemini 4 Argon
Gemini 3.1 Pro Preview and Gemini 4 Argon score almost the same on the Noometry Index (56.7 vs 56.5), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 2 categories and Gemini 4 Argon in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.1 Pro Preview leads 71.8 to 43.9.
- The biggest single-benchmark swing is ProofBench: 26% for Gemini 3.1 Pro Preview and 99% for Gemini 4 Argon.
Side by side
| Gemini 3.1 Pro Preview | Gemini 4 Argon | |
|---|---|---|
| Provider | ||
| Noometry Index | 56.7 | 56.5 |
| Released | 2026-02-19 | 2026-09-30 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $12 | — |
| Results tracked | 71 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 4 Argon leads
Gemini 3.1 Pro Preview: 42.5 (#99), Gemini 4 Argon: 62.0 (#9)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| LMArena WebDev | 1447 | 1678 |
| SciCode | 58.9% | 61.8% |
| LMArena Coding | 1484 | 1550 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| FrontierSWE | — | 55% |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Gemini 4 Argon leads
Gemini 3.1 Pro Preview: 37.7 (#34), Gemini 4 Argon: 49.2 (#8)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | 35.3% | 82.2% |
| Vending-Bench 2 | 3,774 | 13,718 |
| Terminal-Bench | 80.2% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#12), Gemini 4 Argon: 44.2 (#47)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| CritPt | 17.7% | 27.1% |
| LMArena Hard Prompts | 1485 | 1548 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LMCA | 53.8% | — |
| Epoch Capabilities Index | 154.77 | — |
| ForecastBench | 59 | — |
Math Gemini 4 Argon leads
Gemini 3.1 Pro Preview: 62.1 (#34), Gemini 4 Argon: 73.9 (#17)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| ProofBench | 26% | 99% |
| LMArena Math | 1485 | 1536 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
Knowledge Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.8 (#3), Gemini 4 Argon: 43.9 (#89)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1485 | 1553 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Vectara Hallucination Rate | 10.4% | — |
Multimodal Gemini 4 Argon leads
Gemini 3.1 Pro Preview: 37.9 (#69), Gemini 4 Argon: 46.5 (#14)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| Blueprint-Bench 2 | 26.5% | 54.4% |
| LMArena Vision | 1296 | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
Multilingual Gemini 4 Argon leads
Gemini 3.1 Pro Preview: 57.0 (#12), Gemini 4 Argon: 60.3 (#1)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1477 | 1523 |
| LMArena Chinese | 1529 | 1610 |
| LMArena Russian | 1498 | 1537 |
| LMArena Spanish | 1479 | 1497 |
| LMArena French | 1487 | — |
| LMArena German | 1491 | — |
| LMArena Japanese | 1493 | — |
| LMArena Korean | 1455 | — |
Instruction Following Gemini 4 Argon leads
Gemini 3.1 Pro Preview: 77.0 (#32), Gemini 4 Argon: 80.1 (#2)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1466 | 1538 |
Long Context Too close to call
Gemini 3.1 Pro Preview: 47.4 (#18), Gemini 4 Argon: 47.6 (#15)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1483 | 1549 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
Writing & Preference Gemini 4 Argon leads
Gemini 3.1 Pro Preview: 66.1 (#37), Gemini 4 Argon: 71.4 (#19)
| Benchmark | Gemini 3.1 Pro Preview | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1481 | 1534 |
| LMArena Creative Writing | 1482 | 1531 |
| LMArena Multi-Turn | 1488 | 1557 |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than Gemini 4 Argon?
Gemini 3.1 Pro Preview and Gemini 4 Argon score almost the same on the Noometry Index (56.7 vs 56.5), so choose on price, context window or the category you care about most.
Is Gemini 3.1 Pro Preview or Gemini 4 Argon better for coding?
Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 42.5 in the Noometry coding category.
How many benchmarks do Gemini 3.1 Pro Preview and Gemini 4 Argon share?
20 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Gemini 4 Argon has 21.