Gemini 4 Neon
GoogleProprietaryReleased Nov 18, 2026
On the arena.ai Agents leaderboard, Gemini 4 Neon has a Net Improvement of 18.41% (High, rank #3, 95% interval 15.90%–20.93%). Gemini 4 Neon ranks #3 on the LMArena Text leaderboard (style control) with an Arena score of 1512.9 (±8.5, 5,555 votes). Artificial Analysis Intelligence Index: 61.4. API price: $3.00 input / $15.00 output per 1M tokens. Context: 1.05M. Nearest rivals: Gemini 4 Argon (1519.6) above and Muse Wonder (1511.4) below.
Quick answer
- Agents leaderboard
- #3 of 61 · 18.41% success
- Text (LMArena)
- #3 · 1512.9
- 17NAS overall
- #3 of 60
- API price (in / out)
- $3.00 / $15.00 per 1M tokens
- Closest rival
- Gemini 4 Argon · 1519.6
- Cheaper alternative
- Muse Spark 1.3: Text 1498.4, output $4.25 (72% cheaper)
- Data updated
- Nov 21, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Rank history
LMArena rank, last 3 days#3 on Nov 19, #3 now; best #3 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) |
|---|---|---|---|---|---|
| xhighUsed in table | 61.4 | 66.8 | 110 | 119 | 119 |
| high | 59.6 | 64.9 | 105 | 28 | 28 |
| medium | 54.9 | 60.9 | 100 | 33 | 33 |
| low | 44.1 | 52.0 | 125 | 14 | 14 |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 1 | 1527.0 | 60.0 | $20.00 | 83 | |
| 2 | 1519.6 | 50.4 | $20.00 | 95 | |
| 3 | 1512.9 | 61.4 | $15.00 | 110 | |
| 4 | 1511.4 | 43.6 | $20.00 | 139 | |
| 5 | 1506.0 | 59.1 | $20.00 | 96 | |
| 6 | 1504.1 | – | $50.00 | 66 |
More from Google
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 1 | 1527.0 | 60.0 | $20.00 | 83 | |
| 2 | 1519.6 | 50.4 | $20.00 | 95 | |
| 12 | 1497.3 | 30.8 | $3.75 | 118 | |
| 15 | 1489.9 | – | $3.75 | – | |
| 16 | 1489.8 | 53.9 | $7.50 | 219 | |
| 21 | 1486.8 | – | $12.00 | 135 |
Pricing
- Official API list price: $3.00 input and $15.00 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $6.00 per 1M tokens.
- Among 99 models with an output price, it is the #79 cheapest.
- The cheapest OpenRouter route charges $3.00 input / $15.00 output.
Sources & methodology
On the arena.ai Agents leaderboard, Gemini 4 Neon has a Net Improvement of 18.41% (High, rank #3, 95% interval 15.90%–20.93%).
- 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 4 Neon do on the Agents leaderboard?
On the arena.ai Agents leaderboard, Gemini 4 Neon has a Net Improvement of 18.41% (High, rank #3, 95% interval 15.90%–20.93%).
What rank is Gemini 4 Neon right now?
Gemini 4 Neon is #3 on our leaderboard of 85 scored models (Arena score 1512.9); its raw LMArena rank is #3.
What does Gemini 4 Neon cost via API?
Input $3.00 / output $15.00 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 $6.00 per 1M tokens.
How fast is Gemini 4 Neon?
Artificial Analysis measures about 110 output tokens per second, 119 s to the first token and 119 s to the first answer token; it is a reasoning model, so latency includes thinking time.
How close is Gemini 4 Neon to the models ranked next to it?
It is 6.7 points behind Gemini 4 Argon (1519.6) and 1.5 points ahead of Muse Wonder (1511.4); gaps smaller than the confidence interval (±8.5) are not significant.
Is Gemini 4 Neon open source? Can it be self-hosted?
Gemini 4 Neon is a closed model, available only via official APIs or hosted services.
What is the context length of Gemini 4 Neon?
1.05M (1,048,576 tokens, as listed on OpenRouter).
Gemini 4 Neon vs Gemini 4 Argon: which is better?
On the LMArena Text leaderboard Gemini 4 Neon scores 1512.9 and Gemini 4 Argon scores 1519.6 (a 6.7-point gap, within the confidence interval, so not significant). Agent task success: Gemini 4 Neon 18.41%, Gemini 4 Argon 10.31%. On price, Gemini 4 Neon costs $15.00 and Gemini 4 Argon $20.00 per 1M output tokens.
Is there a cheaper model close to Gemini 4 Neon?
Yes: Muse Spark 1.3 scores 1498.4 on the Text leaderboard (Gemini 4 Neon: 1512.9) and costs $4.25 per 1M output tokens, about 72% less than Gemini 4 Neon ($15.00).
Where does the Gemini 4 Neon 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 21, 2026.