Model comparison
Claude Opus 4.8 vs Gemini 3.8 Flash
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 60.7 on the Noometry Index.
Last verified . 47 shared benchmarks.
GoogleSummary
- They share 47 benchmarks with published results for both. Claude Opus 4.8 scores higher in 4 categories and Gemini 3.8 Flash in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.8 Flash leads 74.8 to 61.3.
- The biggest single-benchmark swing is FrontierMath Tier 4: 56.1% for Claude Opus 4.8 and 22% for Gemini 3.8 Flash.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $5 / $25 for Claude Opus 4.8.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 4.8 | Gemini 3.8 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 60.7 | 61.8 |
| Released | 2026-05-28 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $5 | $0.75 |
| Output $ / M tokens | $25 | $3.75 |
| Results tracked | 65 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Opus 4.8: 59.9 (#12), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| DeepSWE | 59% | 73.8% |
| FrontierCode | 46.5% | 41.2% |
| LMArena WebDev | 1556 | 1584 |
| SciCode | 53.5% | 56.6% |
| WeirdML | 82.9% | 84.8% |
| LMArena Coding | 1490 | 1510 |
| ALE-Bench | 1,564 | 1,270 |
| CursorBench | — | 39.6% |
| FrontierSWE | — | 19.6% |
| GSO | 47.1% | — |
Agentic & Tool Use Claude Opus 4.8 leads
Claude Opus 4.8: 47.6 (#11), Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | 48.9% | 64.3% |
| Remote Labor Index | 8.3% | 5.8% |
| GDP.pdf | 24% | 23.4% |
| Vending-Bench 2 | 5,787 | 5,094 |
| OSWorld 2.0 | 20.6% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| LMArena Search | 1204 | — |
Reasoning Gemini 3.8 Flash leads
Claude Opus 4.8: 64.7 (#16), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| ARC-AGI-2 | 72.1% | 89.2% |
| NYT Connections (extended) | 91.1% | 97.4% |
| ARC-AGI-1 | 92.5% | 98.5% |
| CritPt | 20.9% | 18.3% |
| Chess Puzzles | 34% | 61% |
| LMArena Hard Prompts | 1482 | 1508 |
| Mystery Game Puzzles | 36% | 47% |
| DTBench | 94.9% | 95.7% |
| LMCA | 57.5% | 52.9% |
| Surface Evolver Bench | 87.5% | 76.9% |
| Epoch Capabilities Index | 158.21 | 156.71 |
| SimpleBench | 64.8% | — |
| Kagi LLM Benchmark | 88.8% | — |
| EnigmaEval | 23.5% | — |
| EBR-Bench | 28.6% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |
Math Claude Opus 4.8 leads
Claude Opus 4.8: 78.4 (#13), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 80% | 68.4% |
| FrontierMath Tier 4 | 56.1% | 22% |
| OTIS Mock AIME 2024-2025 | 98.3% | 98.9% |
| ProofBench | 69% | 48% |
| LMArena Math | 1487 | 1528 |
| MathArena Final-Answer Competitions | 91.8% | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Gemini 3.8 Flash leads
Claude Opus 4.8: 61.3 (#29), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | 91% | 95.4% |
| SimpleQA Verified | 53% | 69.7% |
| LMArena Expert | 1502 | 1524 |
| Humanity's Last Exam | — | 44.5% |
Multimodal Claude Opus 4.8 leads
Claude Opus 4.8: 42.9 (#26), Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 1294 | 1314 |
| Blueprint-Bench 2 | 14.5% | 38.6% |
| Furniture Assembly | 42.5% | 31.7% |
| LMArena Document | 1475 | — |
Multilingual Gemini 3.8 Flash leads
Claude Opus 4.8: 55.2 (#33), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1450 | 1491 |
| LMArena Chinese | 1507 | 1554 |
| LMArena French | 1481 | 1498 |
| LMArena German | 1472 | 1493 |
| LMArena Japanese | 1440 | 1502 |
| LMArena Korean | 1432 | 1459 |
| LMArena Russian | 1474 | 1515 |
| LMArena Spanish | 1466 | 1485 |
Instruction Following Too close to call
Claude Opus 4.8: 77.4 (#24), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1476 | 1490 |
Long Context Too close to call
Claude Opus 4.8: 45.4 (#35), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1483 | 1508 |
Writing & Preference Too close to call
Claude Opus 4.8: 72.0 (#16), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | Claude Opus 4.8 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1461 | 1499 |
| LMArena Creative Writing | 1454 | 1492 |
| EQ-Bench Creative Writing | 1840 | 1748 |
| LMArena Multi-Turn | 1476 | 1501 |
| EQ-Bench 4 | 1281 | — |
Frequently asked questions
Is Claude Opus 4.8 better than Gemini 3.8 Flash?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 60.7 on the Noometry Index.
Which is cheaper, Claude Opus 4.8 or Gemini 3.8 Flash?
Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Opus 4.8 lists at $5 and $25.
Is Claude Opus 4.8 or Gemini 3.8 Flash better for coding?
They score almost the same on coding (59.9 vs 59.2); test both on your own repository before choosing.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 4.8 and Gemini 3.8 Flash share?
47 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Gemini 3.8 Flash has 50.