← comparisons · head to head
Gemini 3.8 Flash vs Claude Sonnet 5
Of the 5 public leaderboards that rate both, Gemini 3.8 Flash scores higher on 4 and Claude Sonnet 5 on 1. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Gemini 3.8 Flash is at 50 and Claude Sonnet 5 at 36.7 (out of 100).
Scores as published by each board; table composed September 28, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Gemini 3.8 Flash | Claude Sonnet 5 | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,580 | 1,538.9 | Gemini 3.8 Flash |
| LiveBench global average (0-100) | 75.8 | 76 | Claude Sonnet 5 |
| SimpleBench AVG@5 % (private set) | 82.4 | 60.6 | Gemini 3.8 Flash |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 62.3 | 59.6 | Gemini 3.8 Flash |
| Artificial Analysis intelligence index · measured runs only | 40.9 | 38.2 | Gemini 3.8 Flash |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
For coding
On the ArtificialWatch coding index, Gemini 3.8 Flash is at 50 (#15 of 31) and Claude Sonnet 5 at 56.7 (#11). Gemini 3.8 Flash scores higher on 1 of the 3 coding boards that rate both and Claude Sonnet 5 on 2.
| Coding board | Gemini 3.8 Flash | Claude Sonnet 5 |
|---|---|---|
| LMArena · Coding | 1,532.1 | 1,519.3 |
| LiveBench · Coding | 63.4 | 70 |
| Vals Vibe Code Bench | 78.7 | 81.3 |
Gemini 3.8 Flash at a glance
- Developer
- Status
- Live since September 2, 2026
- API price
- $0.75 input / $3.75 output per 1M tokens · Google, gemini-3.8-flash
- Context window
- 1.05M tokens
Live — GA Sep 2 · $0.75/$3.75 per 1M introductory through Dec 31, identical to 3.7 · 1M in / 64K out · 'our most intelligent Flash model' · 20 days after 3.7.
Gemini 3.8 Flash is GA — same price as 3.7, twenty days later
2026-09-02 · Google released Gemini 3.8 Flash today. The Gemini API changelog for September 2 reads: "Gemini 3.8 Flash generally available (GA): Released gemini-3.8-flash, our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows."
Claude Sonnet 5 at a glance
- Developer
- Anthropic
- Status
- Live since June 30, 2026
- API price
- $2 input / $10 output per 1M tokens · Anthropic, claude-sonnet-5
- Context window
- 1M tokens
Shipped Jun 30.
Gemini 3.8 Flash vs Claude Sonnet 5: quick answers
Which is better, Gemini 3.8 Flash or Claude Sonnet 5?
It depends on what you measure. Of the 5 public leaderboards that rate both, Gemini 3.8 Flash scores higher on 4 and Claude Sonnet 5 on 1. Gemini 3.8 Flash's widest lead is on SimpleBench; Claude Sonnet 5's widest lead is on LiveBench. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Gemini 3.8 Flash is at 50 and Claude Sonnet 5 at 36.7 (out of 100).
Which is newer, Gemini 3.8 Flash or Claude Sonnet 5?
Gemini 3.8 Flash. It went live on September 2, 2026, 64 days after Claude Sonnet 5 (June 30, 2026).
Which is cheaper, Gemini 3.8 Flash or Claude Sonnet 5?
Gemini 3.8 Flash is cheaper on both input and output. On each vendor's own API, Gemini 3.8 Flash is $0.75 input / $3.75 output per million tokens and Claude Sonnet 5 is $2 input / $10 output per million tokens. Prices as published in the models.dev catalog, as of 2026-09-27.
Which has the bigger context window, Gemini 3.8 Flash or Claude Sonnet 5?
Gemini 3.8 Flash, at 1.05M tokens against Claude Sonnet 5's 1M, as each vendor lists it.
How do Gemini 3.8 Flash and Claude Sonnet 5 compare for coding?
On the ArtificialWatch coding index, Gemini 3.8 Flash is at 50 (#15 of 31) and Claude Sonnet 5 at 56.7 (#11). Gemini 3.8 Flash scores higher on 1 of the 3 coding boards that rate both and Claude Sonnet 5 on 2.
Who makes Gemini 3.8 Flash and Claude Sonnet 5?
Gemini 3.8 Flash is from Google; Claude Sonnet 5 is from Anthropic.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed September 28, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear the minute the next one drops. Free.
A free Chrome push the moment a new model answers on a public API, an email about 15 minutes later. Texts or a phone call on paid plans.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · the wire