GPT-5.6 Luna
OpenAIProprietaryReleased Jul 9, 2026
On the arena.ai Agents leaderboard, GPT-5.6 Luna has a task success rate of -2.33% (Xhigh, rank #33, 95% interval -3.07%–-1.59%). GPT-5.6 Luna ranks #75 on the LMArena Text leaderboard (style control) with an Arena score of 1452.5 (±4.3, 41,052 votes). Artificial Analysis Intelligence Index: 37.3. API price: $0.20 input / $1.20 output per 1M tokens. Context: 1.05M. Nearest rivals: Hy3 (1453.4) above and Kimi K2.5 (1449.9) below.
Quick answer
- Agents leaderboard
- #33 of 45 · -2.33% success
- Text (LMArena)
- #75 · 1452.5
- 17NAS overall
- #33 of 86
- API price (in / out)
- $0.20 / $1.20 per 1M tokens
- Closest rival
- Hy3 · 1453.4
- Cheaper alternative
- Hy3: Text 1453.4, output $0.56 (54% cheaper)
- Data updated
- Oct 22, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Reasoning effort comparison
Artificial Analysis measurements per reasoning effort of the same model| Effort | Intelligence | Coding | tok/s | TTFT (s) | First answer (s) |
|---|---|---|---|---|---|
| maxUsed in table | 37.3 | 71.4 | – | – | – |
| xhigh | 34.6 | 68.6 | – | – | – |
| high | 32.1 | 63.3 | – | – | – |
| medium | 25.0 | 50.7 | – | – | – |
| low | 21.0 | 44.2 | – | – | – |
| non-reasoning | 15.5 | 39.3 | – | – | – |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 50 |  Qwen3.7 Plus | 1455.6 | 25.2 | $1.60 | 55 |
| 51 |  Grok 4.6 | 1455.4 | 44.3 | $6.00 | – |
| 52 |  Hy3 | 1453.4 | 25.3 | $0.56 | 89 |
| 53 | GPT-5.6 LunaThis page | 1452.5 | 37.3 | $1.20 | – |
| 54 |  Kimi K2.5 | 1449.9 | 23.5 | $3.00 | – |
| 55 |  MiMo-V2.6-Flash | 1448.8 | 37.9 | $0.28 | 51 |
| 56 | SStep 5 Preview | 1446.3 | 43.7 | $2.70 | 96 |
More from OpenAI
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 18 | GPT-5.6 Sol | 1484.5 | 47.0 | $20.00 | – |
| 21 | GPT-5.5 | 1481.5 | 38.4 | $30.00 | – |
| 25 | GPT-6.1 Sol | 1479.4 | 51.8 | $10.00 | 57 |
| 29 | GPT-6 Astra | 1475.5 | 52.7 | $50.00 | 61 |
| 30 | GPT-5.2 Chat | 1475.5 | – | $14.00 | – |
| 32 | GPT-5.4 | 1475.2 | 39.0 | $15.00 | – |
Pricing
- Official API list price: $0.20 input and $1.20 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $0.45 per 1M tokens.
- Among 81 models with an output price, it is the #16 cheapest.
- The cheapest OpenRouter route charges $0.20 input / $1.20 output.
Sources & methodology
On the arena.ai Agents leaderboard, GPT-5.6 Luna has a task success rate of -2.33% (Xhigh, rank #33, 95% interval -3.07%–-1.59%).
- arena.ai Agents — agent task success rate, 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 GPT-5.6 Luna do on the Agents leaderboard?
On the arena.ai Agents leaderboard, GPT-5.6 Luna has a task success rate of -2.33% (Xhigh, rank #33, 95% interval -3.07%–-1.59%).
What rank is GPT-5.6 Luna right now?
GPT-5.6 Luna is #53 on our leaderboard of 69 scored models (Arena score 1452.5); its raw LMArena rank is #75.
What does GPT-5.6 Luna cost via API?
Input $0.20 / output $1.20 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 $0.45 per 1M tokens.
How close is GPT-5.6 Luna to the models ranked next to it?
It is 0.9 points behind Hy3 (1453.4) and 2.6 points ahead of Kimi K2.5 (1449.9); gaps smaller than the confidence interval (±4.3) are not significant.
Is GPT-5.6 Luna open source? Can it be self-hosted?
GPT-5.6 Luna is a closed model, available only via official APIs or hosted services.
What is the context length of GPT-5.6 Luna?
1.05M (1,050,000 tokens, as listed on OpenRouter).
GPT-5.6 Luna vs Hy3: which is better?
On the LMArena Text leaderboard GPT-5.6 Luna scores 1452.5 and Hy3 scores 1453.4 (a 0.9-point gap, within the confidence interval, so not significant). Agent task success: GPT-5.6 Luna -2.33%, Hy3 -6.17%. On price, GPT-5.6 Luna costs $1.20 and Hy3 $0.56 per 1M output tokens.
Is there a cheaper model close to GPT-5.6 Luna?
Yes: Hy3 scores 1453.4 on the Text leaderboard (GPT-5.6 Luna: 1452.5) and costs $0.56 per 1M output tokens, about 54% less than GPT-5.6 Luna ($1.20).
Where does the GPT-5.6 Luna 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 Oct 22, 2026.