GPT-5-Codex vs GPT-6.1 Sol
Full profiles: GPT-5-Codex (OpenAI) and GPT-6.1 Sol (OpenAI): every benchmark, price and rank.
Updated · Data from 9 sources
As of 29 Oct 2026, GPT-6.1 Sol is ahead of GPT-5-Codex on quality (67.2 vs 58.6 on the BenchLeader Index), but GPT-5-Codex is 1.2× cheaper at $3.44 vs $4.00 per 1M tokens blended. Choose GPT-5-Codex for agents & tools (67 vs 64) and fast first answers (10.9 s vs 249.5 s), where it also streams 3×+ faster; choose GPT-6.1 Sol for coding (72 vs 59), multimodal (66 vs 56), and long context (66 vs 61).
Key facts (as of 29 Oct 2026)
- GPT-5-Codex scores 58.6 on the BenchLeader Index and GPT-6.1 Sol scores 67.2 (BenchLeader, 29 Oct 2026).
- GPT-5-Codex costs $3.44 per 1M tokens blended (list price, 29 Oct 2026).
- GPT-6.1 Sol costs $4.00 per 1M tokens blended (list price, 29 Oct 2026).
- GPT-5-Codex streams 3×+ faster than GPT-6.1 Sol (Artificial Analysis, 7-day median, 29 Oct 2026).
- Of the 5 benchmarks both models have, GPT-6.1 Sol leads 5 (BenchLeader, 29 Oct 2026).
GPT-5-Codex benchmarks Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | GPT-6.1 Sol | 72 vs 59 category score | High |
| Agents & tool use | GPT-5-Codex | 67 vs 64 category score | Medium |
| Long documents | GPT-6.1 Sol | 66 vs 61 category score; AA-LCR v1.1 83.0% vs 71.7% | Medium |
| Images and other media | GPT-6.1 Sol | 66 vs 56 category score; MMMU-Pro 86.0% vs 73.8% | High |
| Chat quality (human preference) | – | Only GPT-6.1 Sol has an Arena rating (67 category score) | Not comparable |
| Lowest cost | GPT-5-Codex | $3.44 vs $4.00 per 1M blended; agentic coding session $0.115 vs $0.160 | – |
| Fastest first answer | GPT-5-Codex | 10.9 s (GPT-5-Codex (high)) vs 249.5 s (GPT-6.1 Sol (max)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- GPT-6.1 Sol (max) leads on quality: 67.2 vs 58.6.
- GPT-5-Codex (high) is stronger in agents & tools, instruction following.
- GPT-6.1 Sol (max) is stronger in coding, long context, multimodal, human preference, knowledge, maths, reasoning.
- GPT-5-Codex (high) is 1.2× cheaper ($3.44 vs $4.00 per 1M blended).
- GPT-5-Codex (high) streams 2.5× faster (195 vs 79 tokens per second).
At a glance
| Spec | GPT-5-Codex | GPT-6.1 Sol |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | 15 Sept 2025 | 29 Sept 2026 |
| Context window (tokens) | 400,000 | 1,050,000 |
| Compared at | GPT-5-Codex (high) | GPT-6.1 Sol (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $1.25 / $10.00 / $0.125 | $2.00 / $10.00 / $0.100 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | GPT-5-Codex (high) | GPT-6.1 Sol (max) | Leader |
|---|---|---|---|
| Reasoning | – | 73.2 | not comparable |
| Coding | 58.5 | 71.6 | GPT-6.1 Sol |
| Agents & tools | 66.8 | 64.4 | GPT-5-Codex |
| Maths | – | 72.8 | not comparable |
| Knowledge | – | 73.0 | not comparable |
| Instruction following | 72.4 | – | not comparable |
| Human preference | – | 67.1 | not comparable |
| Multimodal | 56.4 | 65.9 | GPT-6.1 Sol |
| Long context | 60.5 | 66.4 | GPT-6.1 Sol |
Where sources disagree
Across the 5 benchmarks both have, GPT-5-Codex leads 0, GPT-6.1 Sol leads 5. Every overall index that rates both puts GPT-6.1 Sol ahead.
| Overall index | GPT-5-Codex (high) | GPT-6.1 Sol (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 58.6 | 67.2 | GPT-6.1 Sol |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | GPT-5-Codex (high) | GPT-6.1 Sol (max) |
|---|---|---|
| Blended price per 1M tokens | $3.44 | $4.00 |
| Input / output per 1M | $1.25 / $10.00 | $2.00 / $10.00 |
| Cached input per 1M | $0.125 | $0.100 |
| Price per task: chat reply | $0.0035 | $0.0038 |
| Price per task: summarize a 30-page report | $0.021 | $0.030 |
| Price per task: code edit | $0.022 | $0.027 |
| Price per task: agentic coding session | $0.115 | $0.160 |
| Price per task: structured extraction | $0.0045 | $0.0060 |
| Cost to run a full benchmark suite | – | $1.27 |
| Output speed | 195 tok/s | 79 tok/s |
| Time to first answer | 10.9 s | 249.5 s |
| Time to a complete answer | 13.4 s | 255.8 s |
Each model is compared at its best-ranked reasoning-effort setting. GPT-5-Codex (high) scores 58.6 and takes 11 s to its first answer token. GPT-6.1 Sol (max) scores 67.2 and takes 249 s to its first answer token; GPT-6.1 Sol (xhigh) scores 64.3 in 97 s, GPT-6.1 Sol (high) scores 64.0 in 28 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
122 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | GPT-5-Codex (high) | GPT-6.1 Sol (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 58.6 | 67.2 |
| Agents & tools score | BenchLeader | 66.8 | 64.4 |
| Coding score | BenchLeader | 58.5 | 71.6 |
| Instruction following score | BenchLeader | 72.4 | – |
| Long context score | BenchLeader | 60.5 | 66.4 |
| Multimodal score | BenchLeader | 56.4 | 65.9 |
| Human preference score | BenchLeader | – | 67.1 |
| Knowledge score | BenchLeader | – | 73.0 |
| Maths score | BenchLeader | – | 72.8 |
| Reasoning score | BenchLeader | – | 73.2 |
| Blended price $/M | BenchLeader | $3.44 | $4.00 |
| Output speed | BenchLeader | 195 tok/s | 79 tok/s |
| Time to first answer | BenchLeader | 10.9 s | 249.5 s |
| Context window | BenchLeader | 400,000 tokens | 1,050,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 95.4% |
| Arena Hard Prompts | Arena (LMArena) | – | 1504 |
| LiveBench 2.0 Reasoning | LiveBench | – | 92.6%† |
| LiveBench 1.0 Reasoning | LiveBench | – | 92.6% |
| GPQA Diamond (AA) | Artificial Analysis | 83.7% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 27.9% | 52.9% |
| HLE-Diamond (AA) | Artificial Analysis | – | 58.8% |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 70.3%† | – |
| ARC-AGI-1 | ARC Prize | – | 96.5% |
| ARC-AGI-2 | ARC Prize | – | 94.2% |
| ARC-AGI-3 | ARC Prize | – | 96.2% |
| CritPt | Artificial Analysis | 5.1% | 31.7% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 68.5% |
| MysteryMechanism | Vals AI | – | 46.4% |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 68.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 80.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 62.8% |
| DTBench | Epoch AI Benchmarking Hub | – | 96.5% |
| Coding | |||
| SciCode | SciCode | – | 54.2% |
| WeirdML | WeirdML | 54.5% | – |
| FrontierCode | Cognition | – | 50.2%† |
| Arena Coding | Arena (LMArena) | – | 1537 |
| Arena WebDev | Arena (LMArena) | – | 1752 |
| LiveBench 2.0 Coding | LiveBench | – | 96.0%† |
| LiveBench 1.0 Coding | LiveBench | – | 80.4% |
Show all 122 benchmarks
| Metric | Publisher | GPT-5-Codex (high) | GPT-6.1 Sol (max) |
|---|---|---|---|
| Coding | |||
| LiveCodeBench | Vals AI | 84.7% | – |
| IOI | Vals AI | – | 96.9% |
| Code Migration | Vals AI | – | 65.1% |
| Code Migration v1.1 | Vals AI | – | 77.3% |
| ProgramBench | Vals AI | – | 3.0% |
| SWE-bench Multimodal | Vals AI | – | 43.5% |
| Vibe Code Bench v1.1 | Vals AI | – | 88.9% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 2743.8 |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 56.1% |
| Startrise Frontend | Startrise | – | 78.6%† |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 49.1% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 40.6% |
| LiveCodeBench (AA) | Artificial Analysis | 84.0% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 44.3%† | 58.2% |
| APEX-Agents | Mercor | – | 60.0% |
| Arena Agent | Arena (LMArena) | – | 13.6 |
| LiveBench Long Agentic | LiveBench | – | 68.7%† |
| LiveBench Browser | LiveBench | – | 93.3%† |
| LiveBench Agentic Coding | LiveBench | – | 54.5% |
| Terminal-Bench Hard | Artificial Analysis | 37.9% | – |
| τ²-Bench Telecom (AA) | Artificial Analysis | 86.8% | – |
| HiL-Bench | Scale AI SEAL | – | 62.3%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 54.8% |
| GDPval-AA v2.1 | Artificial Analysis | – | 1608 |
| Analyst Agent (AA) | Artificial Analysis | – | 50.0% |
| CyberBench | Vals AI | – | 39.3% |
| Finance Agent v2 | Vals AI | – | 52.0% |
| Finance Agent v2.1 | Vals AI | – | 61.8% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 6.3% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 5.4% |
| Legal Research Bench | Vals AI | – | 38.5% |
| Robo-bench | Vals AI | – | 28.3% |
| SREBench | Vals AI | – | 50.8% |
| Tax Agent Bench | Vals AI | – | 21.8% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 55.0% |
| Terminal-Bench Science | Vals AI | – | 52.9% |
| Arena Search | Arena (LMArena) | – | 1250 |
| AutomationBench | Artificial Analysis | – | 64.9% |
| GDP.pdf (AA) | Artificial Analysis | – | 31.0% |
| Harvey LAB-AA v1.1 | Harvey | – | 6.9% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1555 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 58.1% |
| FACTS Search | – | 88.2%† | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 93.7% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 100.0% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 100.0% |
| ProofBench | Vals AI | – | 99.0%† |
| LiveBench Mathematics | LiveBench | – | 96.8% |
| Arena Maths | Arena (LMArena) | – | 1513 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 73.9% |
| LiveBench 2.0 Data Analysis | LiveBench | – | 82.7%† |
| LiveBench Research | LiveBench | – | 83.5%† |
| LiveBench 1.0 Data Analysis | LiveBench | – | 82.7% |
| AA-Omniscience v1.1 | Artificial Analysis | – | 42.0 |
| PRBench Finance | Scale AI SEAL | – | 46.2%† |
| PRBench Legal | Scale AI SEAL | – | 47.9%† |
| BioMysteryBench | Vals AI | – | 79.6% |
| ClaimBench | Vals AI | – | 100.0% |
| Excel Modeling Benchmark | Vals AI | – | 70.8% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 71.1% |
| MedCode | Vals AI | – | 48.8% |
| MedScribe | Vals AI | – | 86.5% |
| Public Benefits Bench v1.1 | Vals AI | – | 59.3% |
| EBR-bench | Epoch AI Benchmarking Hub | – | 54.3% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 35.0% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 61.8% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 48.1% |
| HealthBench Professional (AA) | OpenAI | – | 65.1% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 90.1% |
| LiveBench Instruction Following | LiveBench | – | 74.2% |
| IFBench | Artificial Analysis | 74.2% | – |
| MultiChallenge | Scale AI SEAL | – | 82.0%† |
| Arena Instruction Following | Arena (LMArena) | – | 1485 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1480 |
| EQ-Bench 4 | EQ-Bench | – | 1272† |
| Arena Creative Writing | Arena (LMArena) | – | 1453 |
| Arena Multi-turn | Arena (LMArena) | – | 1483 |
| Arena Longer Queries | Arena (LMArena) | – | 1489 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1288 |
| LiveBench Design | LiveBench | – | 82.1%† |
| MMMU-Pro | Artificial Analysis | 73.8% | 86.0% |
| SAGE | Vals AI | – | 90.5% |
| Code2Video-AA | Artificial Analysis | – | 1369 |
| AA-3D | Artificial Analysis | – | 1119 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 71.7% | 83.0% |
| MLCR | Artificial Analysis | – | 38.3% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 168.4† |
| LiveBench 2.0 | LiveBench | – | 84.1%† |
| LiveBench 1.0 | LiveBench | – | 81.6% |
| AA Intelligence Index v5.0 | Artificial Analysis | – | 54.5 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 24.9 | 51.8 |
| AA Progress Index v1 | Artificial Analysis | 275.1 | 348.5 |
| Vals Index | Vals AI | – | 63.9 |
| Vals Finance Index | Vals AI | – | 55.8% |
| Vals RSI Index | Vals AI | – | 26.6% |
| Vals Science Index | Vals AI | – | 59.6% |
| Vals Router Index | Vals AI | – | 63.9%† |
Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.
What changed
- GPT-5-Codex (high): 1 new result (AA Progress Index v1).
- GPT-6.1 Sol (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $0.72/M to $1.27/M (76% up).
- GPT-6.1 Sol (max): 10 new results (ClaimBench, Code Migration v1.1, Excel Modeling Benchmark v1.1…).
- GPT-6.1 Sol (max): BenchLeader Index 67.9 → 67.4.
- GPT-6.1 Sol (max): 5 score revisions.
- GPT-6.1 Sol (max): 2 score revisions.
- GPT-5-Codex (high): BenchLeader Index 59.0 → 58.5.
- GPT-6.1 Sol (max): 2 new results (LMCA, DTBench).
- GPT-6.1 Sol (max): 2 score revisions.
- GPT-6.1 Sol (max): 2 new results (ProgramBench, Terminal-Bench Science); 1 score revision.
Related comparisons
- GPT-5-Codex vs Claude Opus 5.5
- GPT-5-Codex vs GPT-6 Astra
- GPT-5-Codex vs Claude Fable 5.1
- GPT-6.1 Sol vs Claude Opus 5.5
- GPT-6.1 Sol vs GPT-6 Astra
- GPT-6.1 Sol vs Claude Fable 5.1
- GPT-6.1 Sol vs Claude Fable 5
- GPT-5 Pro vs GPT-6.1 Sol
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
GPT-5-Codex vs GPT-6.1 Sol: questions
- Is GPT-6.1 Sol better than GPT-5-Codex?
- GPT-6.1 Sol (max) leads on quality: 67.2 vs 58.6. The BenchLeader Index combines every independent quality benchmark; GPT-6.1 Sol (max) is ahead overall as of 29 Oct 2026, but check the category scores for your use.
- GPT-5-Codex vs GPT-6.1 Sol: which is cheaper, and will that change?
- GPT-5-Codex is cheaper today: $3.44 against $4.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is GPT-5-Codex or GPT-6.1 Sol better for coding?
- GPT-6.1 Sol scores higher in coding (72 vs 59 on the category index, where 50 is average).
- Which is faster, GPT-5-Codex or GPT-6.1 Sol?
- GPT-5-Codex streams 3×+ faster (195 vs 79 output tokens per second, Artificial Analysis 7-day median).
- Is GPT-5-Codex or GPT-6.1 Sol better for agents and tool use?
- GPT-5-Codex scores higher in agentic tasks (67 vs 64 on the category index, where 50 is average).
More questions (4)
- Which is better for long documents?
- GPT-6.1 Sol scores higher on long-context benchmarks (66 vs 61). GPT-6.1 Sol accepts more context: 1,050,000 against 400,000 tokens for GPT-5-Codex.
- Which has lower latency?
- GPT-5-Codex answers first: 10.9 s against 249.5 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on GPT-5-Codex vs GPT-6.1 Sol?
- Across the 5 benchmarks both have, GPT-5-Codex leads 0, GPT-6.1 Sol leads 5. Every overall index that rates both puts GPT-6.1 Sol ahead.
- When was GPT-6.1 Sol released?
- GPT-6.1 Sol was released on 29 Sept 2026.