Sign Up

GPT-6 Sol

OpenAI
Announcement
GPT-6 Sol launch post cover

Cost/1M tokens

input
$2.00
cached
$0.20
output
$10.00
cache write
$2.50
Context
1.1Mtokens
Released
1mo ago

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.

How it ranks

Against its predecessor, similarly priced models and the models ranked around it.

DeepSWE 1.1

Best pass@1 per model · Higher is better

Not evaluated in DeepSWE 1.1

Arena Text

Best Arena rating per model · Higher is better

Arena #67

  1. 1526
    Gemini 4 CarbonSimilar price
  2. 1487
    Kimi K3Similar price
  3. 1485
    GPT-5.6 SolPredecessor
  4. 1472
    Claude Sonnet 5.5Similar price
  5. 1458
    DeepSeek V4 Pro 0423Nearby rank
  6. 1457
    GLM 5Nearby rank
  7. 1457
    GPT-6 Sol
  8. 1457
    Seed 2.0 ProNearby rank
  9. 1456
    Grok 4.6Nearby rank
  10. 1354
    Command ASimilar price

-28 vs GPT-5.6 Sol (predecessor) · Ahead of 1 of 4 similarly priced models

Arena WebDev

Best Arena rating per model · Higher is better

Arena #15

  1. 1773
    Claude Sonnet 5.5Similar price
  2. 1768
    Gemini 4 CarbonSimilar price
  3. 1679
    GPT-6.1 TerraNearby rank
  4. 1676
    Qwen3.8 Max (0902)Similar price
  5. 1673
    GPT-6 Sol
  6. 1670
    Qwen3.8 MaxNearby rank
  7. 1664
    DeepSeek V4.1 Flash 1017Nearby rank
  8. 1658
    Kimi K3Similar price
  9. 1615
    GPT-5.6 SolPredecessor

+58 vs GPT-5.6 Sol (predecessor) · Ahead of 1 of 4 similarly priced models

Arena Vision

Best Arena rating per model · Higher is better

Arena #47

  1. 1288
    GPT-5.6 SolPredecessor
  2. 1280
    Grok 4.5Similar price
  3. 1280
    Gemini 3.1 Pro PreviewSimilar price
  4. 1263
    Claude Sonnet 5.5Similar price
  5. 1262
    Qwen3.7 PlusNearby rank
  6. 1261
    Claude Sonnet 5Nearby rank
  7. 1258
    GPT-6 Sol
  8. 1256
    Seed 2.0 ProNearby rank
  9. 1255
    GPT-5.6 LunaNearby rank
  10. 1199
    Mistral Medium 3.5Similar price

-30 vs GPT-5.6 Sol (predecessor) · Ahead of 1 of 4 similarly priced models

Arena Search

Best Arena rating per model · Higher is better

Arena #4

  1. 1255
    GPT-5.6 SolPredecessor
  2. 1248
    GPT-6.1 SolNearby rank
  3. 1245
    GPT-6 AstraNearby rank
  4. 1229
    GPT-6 Sol
  5. 1229
    Claude Fable 5Nearby rank
  6. 1227
    Qwen3.8 MaxNearby rank
  7. 1213
    Claude Opus 5.5Similar price
  8. 1205
    Grok 4.5Similar price
  9. 1142
    Sonar ProSimilar price
  10. 1138
    Sonar Reasoning ProSimilar price

-26 vs GPT-5.6 Sol (predecessor) · Ahead of 4 of 4 similarly priced models

Arena Document

Best Arena rating per model · Higher is better

Not ranked on Arena Document yet

Agent Arena

Best IPS score per model · Higher is better

Arena #13

  1. +0.170
    Gemini 4 CarbonSimilar price
  2. +0.160
    Claude Sonnet 5.5Similar price
  3. +0.073
    Claude Fable 5Nearby rank
  4. +0.072
    Claude Opus 5Nearby rank
  5. +0.069
    GPT-6 Sol
  6. +0.053
    Hy4Nearby rank
  7. +0.049
    Kimi K3.1 ProNearby rank
  8. +0.046
    GPT-5.6 SolPredecessor
  9. +0.026
    Grok 4.7Similar price
  10. +0.006
    Kimi K3Similar price

Level with GPT-5.6 Sol (predecessor, overlapping 95% CIs) · Ahead of 2 of 4 similarly priced models

ARC-AGI-2

Best score per model · Higher is better

#9 of 85

  1. 94.2%
    Gemini 4 CarbonSimilar price
  2. 92.5%
    GPT-5.6 SolPredecessor
  3. 91.3%
    Gemini 4 ArgonNearby rank
  4. 90.0%
    Claude Fable 5.1Nearby rank
  5. 89.6%
    GPT-6 Sol
  6. 89.2%
    Claude Fable 5Nearby rank
  7. 89.2%
    Gemini 3.8 FlashNearby rank
  8. 83.9%
    Claude Sonnet 5.5Similar price
  9. 67.1%
    Grok 4.6Similar price
  10. 60.4%
    Kimi K3Similar price

-2.9 pts vs GPT-5.6 Sol (predecessor) · Ahead of 3 of 4 similarly priced models

FrontierMath-Tier-4-v2-Private

Best score per model · Higher is better

#8 of 72

  1. 95.1%
    Gemini 4 CarbonSimilar price
  2. 92.7%
    GPT-6.1 TerraNearby rank
  3. 90.2%
    Claude Fable 5Nearby rank
  4. 90.0%
    GPT-6 Sol
  5. 87.8%
    Claude Fable 5.1Nearby rank
  6. 82.9%
    GPT-5.6 SolPredecessor
  7. 80.5%
    Claude Sonnet 5.5Similar price
  8. 39.0%
    Kimi K3Similar price
  9. 34.1%
    Qwen3.8 Max (0902)Similar price

+7.1 pts vs GPT-5.6 Sol (predecessor) · Ahead of 3 of 4 similarly priced models

FrontierMath-Tiers-1-3-v2-Private

Best score per model · Higher is better

#8 of 87

  1. 90.5%
    Gemini 4 CarbonSimilar price
  2. 90.2%
    Claude Fable 5.1Nearby rank
  3. 89.8%
    GPT-6 Sol
  4. 89.1%
    GPT-5.6 SolPredecessor
  5. 88.8%
    Claude Sonnet 5.5Similar price
  6. 72.2%
    Kimi K3Similar price
  7. 66.0%
    Grok 4.6Similar price

+0.7 pts vs GPT-5.6 Sol (predecessor) · Ahead of 3 of 4 similarly priced models

GPQA diamond

Best score per model · Higher is better

#10 of 161

  1. 96.5%
    Gemini 4 CarbonSimilar price
  2. 95.6%
    Claude Sonnet 5.5Similar price
  3. 94.6%
    GPT-5.4 ProNearby rank
  4. 94.4%
    Gemini 3.1 Pro PreviewNearby rank
  5. 94.3%
    GPT-6 Sol
  6. 94.3%
    GPT-6.1 TerraNearby rank
  7. 94.1%
    Gemini 3.6 FlashNearby rank
  8. 94.0%
    Grok 4.6Similar price
  9. 93.5%
    GPT-5.6 SolPredecessor
  10. 93.1%
    Kimi K3Similar price

+0.8 pts vs GPT-5.6 Sol (predecessor) · Ahead of 2 of 4 similarly priced models

OTIS Mock AIME 2024-2025

Best score per model · Higher is better

#1 of 158

  1. 100.0%
    Claude Sonnet 5.5Similar price
  2. 100.0%
    Gemini 4 ArgonSimilar price
  3. 100.0%
    GPT-5.6 SolPredecessor
  4. 100.0%
    GPT-6 AstraNearby rank
  5. 100.0%
    GPT-6 Sol
  6. 100.0%
    GPT-6.1 SolNearby rank
  7. 100.0%
    GPT-6.1 TerraNearby rank
  8. 100.0%
    Qwen3.8 Max (0902)Similar price
  9. 97.2%
    Kimi K3Similar price

Level with GPT-5.6 Sol (predecessor) · Ahead of 1 of 4 similarly priced models

SimpleQA Verified

Best score per model · Higher is better

#17 of 87

  1. 77.7%
    Gemini 4 CarbonSimilar price
  2. 69.7%
    GPT-5.6 SolPredecessor
  3. 66.2%
    Gemini 3.6 FlashNearby rank
  4. 63.0%
    GPT-5.5Nearby rank
  5. 60.7%
    GPT-6 Sol
  6. 60.3%
    Muse Spark 1.2Nearby rank
  7. 59.9%
    Claude Opus 5Nearby rank
  8. 56.0%
    Grok 4.7Similar price
  9. 50.6%
    Kimi K3Similar price
  10. 46.5%
    Claude Sonnet 5.5Similar price

-9.0 pts vs GPT-5.6 Sol (predecessor) · Ahead of 3 of 4 similarly priced models

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Reasoning effort

ARC-AGI-2

Score by reasoning effort · Higher is better

All published scores

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.