Model comparison
Claude Opus 4.8 vs Gemini 2.5 Flash
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 12× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.
Last verified . 35 shared benchmarks.
GoogleSummary
- They share 35 benchmarks with published results for both. Claude Opus 4.8 scores higher in 9 categories and Gemini 2.5 Flash in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.8 leads 64.7 to 18.1.
- The biggest single-benchmark swing is ARC-AGI-2: 72.1% for Claude Opus 4.8 and 2.5% for Gemini 2.5 Flash.
- Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $5 / $25 for Claude Opus 4.8.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 4.8 | Gemini 2.5 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 60.7 | 39.3 |
| Released | 2026-05-28 | 2025-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $5 | $0.30 |
| Output $ / M tokens | $25 | $2.50 |
| Results tracked | 65 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.8 leads
Claude Opus 4.8: 59.9 (#12), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| WeirdML | 82.9% | 41.9% |
| LMArena Coding | 1490 | 1424 |
| ALE-Bench | 1,564 | 661.88 |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| LMArena WebDev | 1556 | — |
| SciCode | 53.5% | — |
| GSO | 47.1% | — |
Agentic & Tool Use Claude Opus 4.8 leads
Claude Opus 4.8: 47.6 (#11), Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| Vending-Bench 2 | 5,787 | 548.84 |
| Terminal-Bench | — | 17.1% |
| APEX-Agents | 48.9% | — |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| TheAgentCompany | — | 41.1% |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| BALROG | — | 33.5% |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
Reasoning Claude Opus 4.8 leads
Claude Opus 4.8: 64.7 (#16), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| ARC-AGI-2 | 72.1% | 2.5% |
| SimpleBench | 64.8% | 41.2% |
| Kagi LLM Benchmark | 88.8% | 56.8% |
| ARC-AGI-1 | 92.5% | 33.3% |
| CritPt | 20.9% | 1.1% |
| EnigmaEval | 23.5% | 2.7% |
| LMArena Hard Prompts | 1482 | 1422 |
| DTBench | 94.9% | 76.5% |
| LMCA | 57.5% | 27.5% |
| Epoch Capabilities Index | 158.21 | 143.03 |
| ForecastBench | 59.9 | 60.6 |
| NYT Connections (extended) | 91.1% | — |
| Chess Puzzles | 34% | — |
| EBR-Bench | 28.6% | — |
| Mystery Game Puzzles | 36% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Opus 4.8 leads
Claude Opus 4.8: 78.4 (#13), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 73.1% |
| LMArena Math | 1487 | 1415 |
| FrontierMath (Feb 2025 set) | 47.2% | 4.8% |
| FrontierMath Tier 4 (v1) | 31.3% | 4.2% |
| FrontierMath (Tiers 1-3) | 80% | — |
| FrontierMath Tier 4 | 56.1% | — |
| MathArena Final-Answer Competitions | 91.8% | — |
| ProofBench | 69% | — |
| Omni-MATH | — | 38.5% |
Knowledge Claude Opus 4.8 leads
Claude Opus 4.8: 61.3 (#29), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Expert | 1502 | 1426 |
| GPQA Diamond | 91% | — |
| Humanity's Last Exam | — | 12.1% |
| SimpleQA Verified | 53% | — |
| MMLU-Pro | — | 63.9% |
| Confabulations | — | 16.8% |
| Vectara Hallucination Rate | — | 7.8% |
| GPQA (HELM) | — | 39% |
Multimodal Claude Opus 4.8 leads
Claude Opus 4.8: 42.9 (#26), Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | 1294 | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |
| SpatialViz-Bench | — | 36.9% |
Multilingual Claude Opus 4.8 leads
Claude Opus 4.8: 55.2 (#33), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1450 | 1409 |
| LMArena Chinese | 1507 | 1450 |
| LMArena French | 1481 | 1433 |
| LMArena German | 1472 | 1418 |
| LMArena Japanese | 1440 | 1405 |
| LMArena Korean | 1432 | 1385 |
| LMArena Russian | 1474 | 1415 |
| LMArena Spanish | 1466 | 1421 |
Instruction Following Claude Opus 4.8 leads
Claude Opus 4.8: 77.4 (#24), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1476 | 1405 |
| IFEval | — | 89.8% |
Long Context Gemini 2.5 Flash leads
Claude Opus 4.8: 45.4 (#35), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1483 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Claude Opus 4.8 leads
Claude Opus 4.8: 72.0 (#16), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Claude Opus 4.8 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1461 | 1417 |
| LMArena Creative Writing | 1454 | 1400 |
| EQ-Bench Creative Writing | 1840 | 1137 |
| LMArena Multi-Turn | 1476 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| WildBench | — | 81.7% |
| EQ-Bench 4 | 1281 | — |
Frequently asked questions
Is Claude Opus 4.8 better than Gemini 2.5 Flash?
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 12× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.8 or Gemini 2.5 Flash?
Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Claude Opus 4.8 lists at $5 and $25.
Is Claude Opus 4.8 or Gemini 2.5 Flash better for coding?
Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 4.8 and Gemini 2.5 Flash share?
35 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Gemini 2.5 Flash has 54.