Compare
Four models, one page
Pick the models you are actually choosing between. Every row is scaled within itself, so a bar means something next to its neighbours and nothing across rows.
| Specification | Gemini 3.1 Flash Lite PreviewGoogle | Claude Opus 5Anthropic |
|---|---|---|
| Released | Mar 3, 2026 | Jul 24, 2026 |
| Context window | 1.05M | 1M |
| Max output | 66K | 128K |
| Input / 1M | $0.25 | $5 |
| Output / 1M | $1.5 | $25 |
| Cost per task | $0.13 | $2.25 |
| Arena Elo | 1,106 | 1,393 |
| Serving providers | 1 | 5 |
| Parameters | Undisclosed | Undisclosed |
| Licence | Proprietary | Proprietary |
| Capabilities |
|
|
Metrics side by side
Each row is scaled to the largest value in that row — bars compare within a row, never across rows
- Gemini 3.1 Flash Lite Preview
- Claude Opus 5
Intelligence Index
Gemini 3.1 Flash Lite Preview25.6Claude Opus 563.1Coding Index
Gemini 3.1 Flash Lite Preview34.7Claude Opus 578.0Agentic Index
Gemini 3.1 Flash Lite Preview6.5Claude Opus 559.2Output speed
Gemini 3.1 Flash Lite Preview106 t/sClaude Opus 587 t/sContext window
Gemini 3.1 Flash Lite Preview1.05MClaude Opus 51MLatency · lower is better
Gemini 3.1 Flash Lite Preview591msClaude Opus 51.12sBlended price / 1M · lower is better
Gemini 3.1 Flash Lite Preview$0.563Claude Opus 5$10Cost per task · lower is better
Gemini 3.1 Flash Lite Preview$0.13Claude Opus 5$2.25
Rows marked “lower is better” still draw a longer bar for a larger number — read the value, not just the length. Arena Elo is in the specification table above instead: it has no meaningful zero, so a bar would flatten the gaps.
View as table
| Metric | Gemini 3.1 Flash Lite Preview | Claude Opus 5 |
|---|---|---|
| Intelligence Index | 25.6 | 63.1 |
| Coding Index | 34.7 | 78.0 |
| Agentic Index | 6.5 | 59.2 |
| Output speed | 106 t/s | 87 t/s |
| Context window | 1.05M | 1M |
| Latency · lower is better | 591ms | 1.12s |
| Blended price / 1M · lower is better | $0.563 | $10 |
| Cost per task · lower is better | $0.13 | $2.25 |
Evaluation scores
Percentage correct on a common 0–100% scale
- Gemini 3.1 Flash Lite Preview
- Claude Opus 5
GPQA Diamond
Gemini 3.1 Flash Lite Preview82.2%Claude Opus 593.2%Humanity's Last Exam
Gemini 3.1 Flash Lite Preview17.2%Claude Opus 554.9%SciCode
Gemini 3.1 Flash Lite Preview41.9%Claude Opus 555.7%τ²-bench
Gemini 3.1 Flash Lite Preview31.3%Claude Opus 542.1%Terminal-Bench Hard
Gemini 3.1 Flash Lite Preview24.2%Claude Opus 5not measuredAA-LCR long context
Gemini 3.1 Flash Lite Preview71.3%Claude Opus 575.7%
A missing bar means that evaluation was not run for that model — it is not a zero.
View as table
| Evaluation | Gemini 3.1 Flash Lite Preview | Claude Opus 5 |
|---|---|---|
| GPQA Diamond | 82.2% | 93.2% |
| Humanity's Last Exam | 17.2% | 54.9% |
| SciCode | 41.9% | 55.7% |
| τ²-bench | 31.3% | 42.1% |
| Terminal-Bench Hard | 24.2% | — |
| LiveCodeBench | — | — |
| AA-LCR long context | 71.3% | 75.7% |
| AIME 2025 | — | — |
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).