Gemini 3.8 Flash
GoogleProprietaryReleased Sep 2, 2026
On the arena.ai Agents leaderboard, Gemini 3.8 Flash has a Net Improvement of 2.38% (High, rank #17, 95% interval 1.54%–3.23%). Gemini 3.8 Flash ranks #9 on the LMArena Text leaderboard (style control) with an Arena score of 1497.5 (±4.2, 61,143 votes). Artificial Analysis Intelligence Index: 30.8. API price: $0.75 input / $3.75 output per 1M tokens. Context: 1.05M. Nearest rivals: Claude Opus 4.7 (1501.1) above and Muse Spark 1.3 (1496.3) below.
Quick answer
- Agents leaderboard
- #17 of 37 · 2.38% success
- Text (LMArena)
- #9 · 1497.5
- 17NAS overall
- #16 of 36
- API price (in / out)
- $0.75 / $3.75 per 1M tokens
- Closest rival
- Claude Opus 4.7 · 1501.1
- Data updated
- Nov 10, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Rank history
LMArena rank, last 26 days#9 on Oct 16, #9 now; best #9 in this period.
Reasoning effort comparison
Artificial Analysis measurements per reasoning effort of the same model| Effort | Intelligence | Coding | tok/s | TTFT (s) | First answer (s) |
|---|---|---|---|---|---|
| highUsed in table | 30.8 | 38.1 | 123 | 16 | 16 |
| medium | 30.1 | 37.4 | – | – | – |
| low | 22.5 | 32.6 | – | – | – |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 6 | 1503.0 | – | $25.00 | – | |
| 7 | 1502.7 | 49.2 | $50.00 | 68 | |
| 8 | 1501.1 | – | $25.00 | – | |
| 9 | 1497.5 | 30.8 | $3.75 | 123 | |
| 10 | 1496.3 | 36.6 | $4.25 | – | |
| 11 | 1493.5 | – | $4.25 | – | |
| 12 | 1490.7 | – | $4.25 | – |
More from Google
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 1 | 1526.0 | 60.0 | $20.00 | 89 | |
| 2 | 1522.4 | 50.4 | $20.00 | 82 | |
| 14 | 1489.4 | – | $3.75 | – | |
| 18 | 1486.7 | – | $12.00 | 128 | |
| 19 | 1485.6 | – | $12.00 | – | |
| 22 | 1482.5 | – | $3.75 | – |
Pricing
- Official API list price: $0.75 input and $3.75 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $1.50 per 1M tokens.
- Among 79 models with an output price, it is the #29 cheapest.
- The cheapest OpenRouter route charges $0.83 input / $4.13 output.
Sources & methodology
On the arena.ai Agents leaderboard, Gemini 3.8 Flash has a Net Improvement of 2.38% (High, rank #17, 95% interval 1.54%–3.23%).
- arena.ai Agents — agent Net Improvement, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
- LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.
FAQ
How does Gemini 3.8 Flash do on the Agents leaderboard?
On the arena.ai Agents leaderboard, Gemini 3.8 Flash has a Net Improvement of 2.38% (High, rank #17, 95% interval 1.54%–3.23%).
What rank is Gemini 3.8 Flash right now?
Gemini 3.8 Flash is #9 on our leaderboard of 70 scored models (Arena score 1497.5); its raw LMArena rank is #9.
What does Gemini 3.8 Flash cost via API?
Input $0.75 / output $3.75 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $1.50 per 1M tokens.
How fast is Gemini 3.8 Flash?
Artificial Analysis measures about 123 output tokens per second, 16 s to the first token and 16 s to the first answer token; it is a reasoning model, so latency includes thinking time.
How close is Gemini 3.8 Flash to the models ranked next to it?
It is 3.6 points behind Claude Opus 4.7 (1501.1) and 1.2 points ahead of Muse Spark 1.3 (1496.3); gaps smaller than the confidence interval (±4.2) are not significant.
Is Gemini 3.8 Flash open source? Can it be self-hosted?
Gemini 3.8 Flash is a closed model, available only via official APIs or hosted services.
What is the context length of Gemini 3.8 Flash?
1.05M (1,048,576 tokens, as listed on OpenRouter).
Gemini 3.8 Flash vs Claude Opus 4.7: which is better?
On the LMArena Text leaderboard Gemini 3.8 Flash scores 1497.5 and Claude Opus 4.7 scores 1501.1 (a 3.6-point gap, within the confidence interval, so not significant). On price, Gemini 3.8 Flash costs $3.75 and Claude Opus 4.7 $25.00 per 1M output tokens.
Is there a cheaper model close to Gemini 3.8 Flash?
Among models within 15 Text points, none is currently more than 30% cheaper than Gemini 3.8 Flash on output price.
Where does the Gemini 3.8 Flash data come from and how often is it updated?
Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Nov 10, 2026.