Model comparison
Gemini 1.5 Pro (May 2024) vs Gemini 3.8 Flash
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 32.1 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and Gemini 3.8 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 12.3.
- The biggest single-benchmark swing is ARC-AGI-2: 0.8% for Gemini 1.5 Pro (May 2024) and 89.2% for Gemini 3.8 Flash.
Side by side
| Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash | |
|---|---|---|
| Provider | ||
| Noometry Index | 32.1 | 61.8 |
| Released | 2024-02-15 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $3.75 |
| Results tracked | 45 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| WeirdML | 22.2% | 84.8% |
| LMArena Coding | 1294 | 1510 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1584 |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 1,270 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| Remote Labor Index | — | 5.8% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |
Reasoning Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| ARC-AGI-2 | 0.8% | 89.2% |
| LMArena Hard Prompts | 1296 | 1508 |
| DTBench | 59% | 95.7% |
| Epoch Capabilities Index | 131.73 | 156.71 |
| SimpleBench | 27.1% | — |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| Mystery Game Puzzles | — | 47% |
| LMCA | — | 52.9% |
| Surface Evolver Bench | — | 76.9% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 98.9% |
| LMArena Math | 1315 | 1528 |
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| ProofBench | — | 48% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | 57.2% | 95.4% |
| Humanity's Last Exam | 4.6% | 44.5% |
| LMArena Expert | 1279 | 1524 |
| SimpleQA Verified | — | 69.7% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 1161 | 1314 |
| Video-MME | 75% | — |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |
Multilingual Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1312 | 1491 |
| LMArena Chinese | 1331 | 1554 |
| LMArena French | 1302 | 1498 |
| LMArena German | 1286 | 1493 |
| LMArena Japanese | 1292 | 1502 |
| LMArena Korean | 1298 | 1459 |
| LMArena Russian | 1320 | 1515 |
| LMArena Spanish | 1311 | 1485 |
Instruction Following Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1297 | 1490 |
| IFEval | 83.7% | — |
Long Context Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1308 | 1508 |
Writing & Preference Gemini 3.8 Flash leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | Gemini 1.5 Pro (May 2024) | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1319 | 1499 |
| LMArena Creative Writing | 1333 | 1492 |
| LMArena Multi-Turn | 1296 | 1501 |
| EQ-Bench Creative Writing | — | 1748 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Gemini 3.8 Flash?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Gemini 3.8 Flash better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Gemini 3.8 Flash share?
25 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Gemini 3.8 Flash has 50.