GPT-6.2 Sol
OpenAIProprietaryPreliminaryReleased Nov 17, 2026
On the arena.ai Agents leaderboard, GPT-6.2 Sol has a Net Improvement of 11.31% (Max, rank #11, 95% interval 8.89%–13.73%). GPT-6.2 Sol ranks #64 on the LMArena Text leaderboard (style control) with an Arena score of 1464.7 (±12.0, 2,541 votes). It has few votes so far, so this is a preliminary result and the rank may move. Artificial Analysis Intelligence Index: 57.3. API price: $2.00 input / $10.00 output per 1M tokens. Context: 1.05M. Nearest rivals: GLM-5.1 (1465.1) above and DeepSeek V4 Pro (1463.8) below.
Quick answer
- Agents leaderboard
- #11 of 61 · 11.31% success
- Text (LMArena)
- #64 · 1464.7
- 17NAS overall
- #10 of 60
- API price (in / out)
- $2.00 / $10.00 per 1M tokens
- Closest rival
- GLM-5.1 · 1465.1
- Cheaper alternative
- GLM-5.3 Flash: Text 1475.3, output $0.50 (95% cheaper)
- Data updated
- Nov 21, 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 | 57.3 | 61.2 | 80 | 195 | 195 |
| xhigh | 55.7 | 59.9 | 71 | 78 | 78 |
| high | 54.9 | 58.7 | 71 | 17 | 17 |
| medium | 52.7 | 56.2 | 64 | 3.1 | 3.1 |
| low | 40.6 | 44.4 | 60 | 2.0 | 2.0 |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 46 | 1466.3 | – | $0.70 | – | |
| 47 | 1465.7 | – | $6.00 | 59 | |
| 48 | 1465.1 | – | $4.07 | 98 | |
| 49 | 1464.7 | 57.3 | $10.00 | 80 | |
| 50 | 1463.8 | 23.1 | $3.96 | 76 | |
| 51 | 1460.9 | – | $4.00 | 40 | |
| 52 | 1460.8 | – | $10.00 | 75 |
More from OpenAI
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 23 | 1485.1 | – | $20.00 | 126 | |
| 26 | 1482.6 | 54.6 | $10.00 | 68 | |
| 29 | 1481.0 | – | $30.00 | 82 | |
| 32 | 1475.3 | 56.9 | $50.00 | 47 | |
| 33 | 1475.3 | – | $14.00 | – | |
| 36 | 1475.1 | – | $15.00 | 90 |
Pricing
- Official API list price: $2.00 input and $10.00 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $4.00 per 1M tokens.
- Among 99 models with an output price, it is the #65 cheapest.
- The cheapest OpenRouter route charges $2.00 input / $10.00 output.
Sources & methodology
On the arena.ai Agents leaderboard, GPT-6.2 Sol has a Net Improvement of 11.31% (Max, rank #11, 95% interval 8.89%–13.73%).
- 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 GPT-6.2 Sol do on the Agents leaderboard?
On the arena.ai Agents leaderboard, GPT-6.2 Sol has a Net Improvement of 11.31% (Max, rank #11, 95% interval 8.89%–13.73%).
What rank is GPT-6.2 Sol right now?
GPT-6.2 Sol is #49 on our leaderboard of 85 scored models (Arena score 1464.7); its raw LMArena rank is #64.
What does GPT-6.2 Sol cost via API?
Input $2.00 / output $10.00 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 $4.00 per 1M tokens.
How fast is GPT-6.2 Sol?
Artificial Analysis measures about 80 output tokens per second, 195 s to the first token and 195 s to the first answer token; it is a reasoning model, so latency includes thinking time.
How close is GPT-6.2 Sol to the models ranked next to it?
It is 0.4 points behind GLM-5.1 (1465.1) and 0.9 points ahead of DeepSeek V4 Pro (1463.8); gaps smaller than the confidence interval (±12.0) are not significant.
Why is GPT-6.2 Sol marked Preliminary?
It has only 2,541 votes on LMArena and a 95% confidence interval of ±12.0; with few votes the score can move noticeably as new votes arrive, so treat the rank as provisional. We mark models with fewer than 5,000 votes or ± above 10 as Preliminary.
Is GPT-6.2 Sol open source? Can it be self-hosted?
GPT-6.2 Sol is a closed model, available only via official APIs or hosted services.
What is the context length of GPT-6.2 Sol?
1.05M (1,050,000 tokens, as listed on OpenRouter).
GPT-6.2 Sol vs GLM-5.1: which is better?
On the LMArena Text leaderboard GPT-6.2 Sol scores 1464.7 and GLM-5.1 scores 1465.1 (a 0.4-point gap, within the confidence interval, so not significant). On price, GPT-6.2 Sol costs $10.00 and GLM-5.1 $4.07 per 1M output tokens.
Is there a cheaper model close to GPT-6.2 Sol?
Yes: GLM-5.3 Flash scores 1475.3 on the Text leaderboard (GPT-6.2 Sol: 1464.7) and costs $0.50 per 1M output tokens, about 95% less than GPT-6.2 Sol ($10.00).
Where does the GPT-6.2 Sol 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.