Skip to main content
BenchLM
Advertise

Model profile

GPT-5.6 Sol

OpenAICurrentReleased Jul 9, 2026
Data verified
Overall Score
81.96Public #3 of 200Verified #3 of 99
Arena Elo
1486
Eligible category ranks
4of 8
Price (1M tokens)
$5 in / $30 out
API pricing
Speed
Not listed
Context
1M

Evidence coverage

47 of 323 tracked benchmarks are published. 26 are verified and 21 provisional. 7 of 8 categories are measured.

Updated July 23, 2026Methodology
Published / tracked
47 / 323
Verified
26
Provisional
21
Categories with evidence
7 / 8

Evidence by category

  • Agentic17 benchmarks
    Mixed evidence
  • Coding8 benchmarks
    Mixed evidence
  • Reasoning4 benchmarks
    Mixed evidence
  • Knowledge10 benchmarks
    Mixed evidence
  • Math3 benchmarks
    Verified
  • Multilingual0 benchmarks
    Not measured
  • Multimodal3 benchmarks
    Mixed evidence
  • Inst. Following1 benchmark
    Reported
ProprietaryReasoning
Confidence:
High
sol

GPT-5.6 Sol ranks #3 out of 200 models on the public leaderboard with an overall score of 81.96/100. It also ranks #3 out of 99 on the verified leaderboard. This places it among the top tier of AI models available in 2026, competing directly with the strongest models from leading AI labs.

GPT-5.6 Sol is a proprietary model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

GPT-5.6 Sol sits inside the GPT-5.6 family alongside GPT-5.6 Terra, GPT-5.6 Luna. BenchLM links it directly to GPT-5.5 as the earlier related model in that lineage. This profile currently has 47 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Agentic (#1), while its weakest is Knowledge (#9). This performance profile makes it particularly useful for coding agents, browser research, and computer-use workflows.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 76.72–83.93

  1. Claude Mythos 5
    Anthropic
    #183.93
    Claude Mythos 5 is #1 with a score of 83.93.
    Compare
  2. Claude Fable 5
    Anthropic
    #283.68
    Claude Fable 5 is #2 with a score of 83.68.
    Compare
  3. GPT-5.6 SolCurrent model
    OpenAI
    #381.96
    GPT-5.6 Sol is #3 with a score of 81.96.
  4. Kimi K3
    Moonshot AI
    #480.96
    Kimi K3 is #4 with a score of 80.96.
    Compare
  5. Claude Opus 4.8
    Anthropic
    #578.34
    Claude Opus 4.8 is #5 with a score of 78.34.
    Compare
  6. Muse Spark 1.1
    Meta
    #677.44
    Muse Spark 1.1 is #6 with a score of 77.44.
    Compare
  7. Grok 4.5
    xAI
    #776.72
    Grok 4.5 is #7 with a score of 76.72.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Agentic100%
    Eligible cohort rank #1 of 119Category score 75.2
  2. Multimodal93%
    Eligible cohort rank #3 of 29Category score 84.3
  3. Coding98%
    Eligible cohort rank #3 of 122Category score 78.9
  4. Knowledge84%
    Eligible cohort rank #9 of 52Category score 83.2

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #1 of 119Percentile 100thWeight 22%17 benchmarksMixed sources75.2
CodingRank #3 of 122Percentile 98thWeight 20%8 benchmarksMixed sources78.9
ReasoningWeight 17%4 benchmarksMixed sourcesScore pending
KnowledgeRank #9 of 52Percentile 84thWeight 12%10 benchmarksMixed sources83.2
MathRank Not rankedWeight 5%3 benchmarksVerified97.1
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank #3 of 29Percentile 93rdWeight 12%3 benchmarksMixed sources84.3
Inst. FollowingWeight 5%1 benchmarkReportedScore pending

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1486±8.35,467
Coding1526±15.61,550
Math1470±34.4259
Instruction Following1484±14.41,787
Creative Writing1481±20.3945
Multi-turn1480±20.4901
Hard Prompts1506±10.33,559
Hard Prompts (English)1513±15.81,445
Longer Query1489±13.02,324

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic17 benchmarks
Terminal-Bench 2.0Provider exact
91.9%Weighted 38%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol Ultra at 91.9% on Terminal-Bench 2.1. BenchLM follows the highest-setting rule and stores this on the existing Terminal-Bench 2 key.
BrowseCompProvider exact
92.2%Weighted 28%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol Ultra at 92.2% on BrowseComp. BenchLM follows the highest-setting rule when a separate Ultra value is published.
OSWorld 2.0Provider exact
62.6%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 62.6% on OSWorld 2.0.
CyberGymProvider exact
84.5%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 84.5% on CyberGym.
ExploitGymProvider exact
33.7%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 33.7% on ExploitGym under the six-hour cap.
ToolathlonProvider exact
58%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 58.0% on Toolathlon.
AA Agentic IndexReported

Artificial Analysis Agentic Index

54.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

85.1%Display only
Source: Artificial Analysis: tau2-bench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

61.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
GDPval-AAProvider exact
1736Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 1747.8 Elo on GDPval-AA v2.
AA BriefcaseReported

Artificial Analysis Briefcase

1501Display only
Source: Artificial Analysis: aa-briefcase leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA ITBenchReported

Artificial Analysis ITBench-AA

56.2%Display only
Source: Artificial Analysis: itbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Tau3 BankingReported

Artificial Analysis Tau3-Banking

33.0%Display only
Source: Artificial Analysis: tau3-banking leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA AutomationBenchReported

Artificial Analysis AutomationBench

51.2%Display only
Source: Artificial Analysis: automationbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Harvey LABReported

Artificial Analysis Harvey LAB-AA

87.2%Display only
Source: Artificial Analysis: harvey-lab-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
terminalBenchHardReported
65.9%Display only
Source: Artificial Analysis: terminalbench-hard leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
aaTerminalBench21Reported
88%Display only
Source: Artificial Analysis: terminalbench-v2-1 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding8 benchmarks
SWE-bench ProProvider exact
64.6%Weighted 10%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 64.6% on SWE-Bench Pro.
Terminal-Bench 2.0Provider exact
91.9%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol Ultra at 91.9% on Terminal-Bench 2.1. BenchLM follows the highest-setting rule and stores this on the existing Terminal-Bench 2 key.
deepSweProvider exact
72.7%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 72.7% on DeepSWE v1.1. BenchLM stores DeepSWE as display-only because the source benchmark is an agent-harness coding signal.
FrontierCode 1.1 ExtendedProvider exact
60.6%Display only
Source: Cognition: GPT-5.6 models in DevinProvenance: Cognition reports GPT-5.6 Sol at 60.6% on the display-only FrontierCode 1.1 Extended subset in Devin.
cursorBench32Benchmark exact
67.2%Display only
Source: Cursor evals: CursorBench 3.2Provenance: Cursor reports GPT-5.6 Sol Max at this exact CursorBench 3.2 score on its public evals page. BenchLM stores it on the GPT-5.6 Sol row as a display-only coding-agent benchmark.
VulcanBench v3Benchmark exact
87.0%Display only
Source: VulcanBench v3 Technical Report No. 4Provenance: VulcanBench v3 reports GPT-5.6 Sol at 87.0% pass@1 at high effort, the model's best published result in the three-effort matrix.
AA Coding IndexReported

Artificial Analysis Coding Index

77.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

56.1%Display only
Source: Artificial Analysis: scicode leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Reasoning4 benchmarks
ARC-AGI-3Benchmark exact

Abstraction and Reasoning Corpus for AGI v3

7.8%Display only
Source: ARC Prize: GPT-5.6 verified resultsProvenance: ARC Prize reports GPT-5.6 Sol (Max) at 7.8% on ARC-AGI-3. This is distinct from ARC-AGI-2 and remains display-only.
GeneBench-ProProvider exact
28.7%Display only
Source: OpenAI: GeneBench-Pro technical reportProvenance: OpenAI reports GPT-5.6 Sol at a 28.7% eval-level pass rate on the 129-problem GeneBench-Pro suite at max reasoning. BenchLM keeps this provider-developed, sparse-coverage benchmark display-only.
AA-LCRReported

Artificial Analysis Long Context Reasoning

73.7%Display only
Source: Artificial Analysis: artificial-analysis-long-context-reasoning leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
CritPtSecondary exact

Critical Physics Tasks

32.3%Display only
Source: Artificial Analysis: CritPt Benchmark LeaderboardProvenance: Artificial Analysis reports GPT-5.6 Sol (max) at 32.3% on CritPt.
Knowledge10 benchmarks
GPQAProvider exact

Graduate-Level Google-Proof Q&A

94.6%Weighted 7%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 94.6% on GPQA Diamond. BenchLM stores the value on both gpqa and gpqaDiamond for consistency with provider launch-table mappings.
GPQA-DProvider exact

GPQA Diamond

94.6%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 94.6% on GPQA Diamond.
HealthBench ProfessionalProvider exact
60.5%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 60.5% on HealthBench Professional using the official scoring approach from the HealthBench Professional paper.
HealthBench HardProvider exact
33.1%Display only
Source: OpenAI GPT-5.6 system cardProvenance: OpenAI's July 9, 2026 GPT-5.6 system card reports the length-adjusted HealthBench Hard score for GPT-5.6 Sol. BenchLM stores it as a display-only health benchmark row.
Artificial Analysis Intelligence IndexProvider exact
58.9%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 58.9 on Artificial Analysis Intelligence Index v4.1. BenchLM keeps this as a display-only Artificial Analysis row.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

94.1%Display only
Source: Artificial Analysis: gpqa-diamond leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

47.2%Display only
Source: Artificial Analysis: humanitys-last-exam leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

21.7%Display only
Source: Artificial Analysis: omniscience leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

58.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

88.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math3 benchmarks
FrontierMath v2 (Tiers 1-3)Provider exact

FrontierMath v2 Tiers 1-3

89.000%Weighted 30%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 89.0% on FrontierMath v2 Tiers 1-3.
FrontierMath v2 (Tier 4)Provider exact

FrontierMath v2 Tier 4

83.000%Weighted 10%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 83.0% on FrontierMath v2 Tier 4.
FrontierMath (legacy)Provider exact

FrontierMath legacy aggregate

89%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 89.0% on FrontierMath v2 Tier 1-3. BenchLM maps the existing FrontierMath field to this Tier 1-3 slice, consistent with the GPT-5.4 Pro mapping; the separate Tier 4 result is not combined.
Multimodal3 benchmarks
MMMU-ProProvider exact

Massive Multi-discipline Multimodal Understanding Pro

83%Weighted 45%
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 83.0% on MMMU Pro without tools.
MMMU-Pro w/ PythonProvider exact

MMMU-Pro with Python

84.6%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 84.6% on MMMU Pro with tools.
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

83.4%Display only
Source: Artificial Analysis: mmmu-pro leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

72.7%Display only
Source: Artificial Analysis: ifbench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
External signals1 benchmark
ExploitBenchProvider exact

ExploitBench v8-bench

74%Display only
Source: OpenAI: GPT-5.6Provenance: OpenAI reports GPT-5.6 Sol at 73.5% on ExploitBench. BenchLM stores this as a display-only external security row.

GPT-5.6 Family

sol · sol

Related Earlier Model

GPT-5.5
GPT-5.6 TerraScore 72.57GPT-5.6 LunaScore 67.17

Frequently Asked Questions

How does GPT-5.6 Sol perform overall in AI benchmarks?

GPT-5.6 Sol currently ranks #3 out of 200 models on BenchLM's provisional leaderboard with an overall score of 81.96. It also ranks #3 out of 99 on the verified leaderboard. It is created by OpenAI. Its published context window is 1M.

Is GPT-5.6 Sol good for knowledge and understanding?

GPT-5.6 Sol ranks #9 out of 52 models in knowledge and understanding benchmarks with an average score of 83.2. It is among the top performers in this category.

Is GPT-5.6 Sol good for coding and programming?

GPT-5.6 Sol ranks #3 out of 122 models in coding and programming benchmarks with an average score of 78.9. It is among the top performers in this category.

Is GPT-5.6 Sol good for mathematics?

GPT-5.6 Sol has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.6 Sol good for reasoning and logic?

GPT-5.6 Sol has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is GPT-5.6 Sol good for agentic tool use and computer tasks?

GPT-5.6 Sol ranks #1 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 75.2. It is among the top performers in this category.

Is GPT-5.6 Sol good for multimodal and grounded tasks?

GPT-5.6 Sol ranks #3 out of 29 models in multimodal and grounded tasks benchmarks with an average score of 84.3. It is among the top performers in this category.

Is GPT-5.6 Sol good for instruction following?

GPT-5.6 Sol has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Which sibling models are related to GPT-5.6 Sol?

GPT-5.6 Sol belongs to the GPT-5.6 family. Related variants on BenchLM include GPT-5.6 Terra, GPT-5.6 Luna.

Does GPT-5.6 Sol have full benchmark coverage on BenchLM?

Not yet. GPT-5.6 Sol currently has 47 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of GPT-5.6 Sol?

GPT-5.6 Sol has a published context window of 1M, which determines how much text it can process in a single interaction.

Related Resources

More from OpenAI LLM Pricing Comparison BenchLM Methodology The AI Race Which LLM Should I Use? Benchmark Explainers
Last updated: July 23, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.