Claude Fable 5 vs GPT-5-Codex
Full profiles: Claude Fable 5 (Anthropic) and GPT-5-Codex (OpenAI): every benchmark, price and rank.
Updated · Data from 10 sources
As of 29 Oct 2026, Claude Fable 5 is ahead of GPT-5-Codex on quality (66.6 vs 58.6 on the BenchLeader Index), but GPT-5-Codex is 5.8× cheaper at $3.44 vs $20.00 per 1M tokens blended. Choose Claude Fable 5 for coding (70 vs 59) and fast first answers (3.8 s vs 10.9 s); choose GPT-5-Codex for agents & tools (67 vs 64), where it also streams 3×+ faster.
Key facts (as of 29 Oct 2026)
- Claude Fable 5 scores 66.6 on the BenchLeader Index and GPT-5-Codex scores 58.6 (BenchLeader, 29 Oct 2026).
- Claude Fable 5 costs $20.00 per 1M tokens blended (list price, 29 Oct 2026).
- GPT-5-Codex costs $3.44 per 1M tokens blended (list price, 29 Oct 2026).
- GPT-5-Codex streams 3×+ faster than Claude Fable 5 (Artificial Analysis, 7-day median, 29 Oct 2026).
- Of the 1 benchmarks both models have, Claude Fable 5 leads 1 (BenchLeader, 29 Oct 2026).
Claude Fable 5 benchmarks 
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 | Claude Fable 5 | 70 vs 59 category score; LiveCodeBench 89.8% vs 84.7% | High |
| Agents & tool use | GPT-5-Codex | 67 vs 64 category score | Medium |
| Chat quality (human preference) | – | Only Claude Fable 5 has an Arena rating (68 category score) | Not comparable |
| Lowest cost | GPT-5-Codex | $3.44 vs $20.00 per 1M blended; agentic coding session $0.115 vs $0.800 | – |
| Fastest first answer | Claude Fable 5 | 3.8 s (Claude Fable 5) vs 10.9 s (GPT-5-Codex (high)) 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
- Claude Fable 5 leads on quality: 66.6 vs 58.6.
- Claude Fable 5 is stronger in coding, human preference, knowledge, reasoning.
- GPT-5-Codex (high) is stronger in agents & tools, instruction following, long context, multimodal.
- GPT-5-Codex (high) is 5.8× cheaper ($3.44 vs $20.00 per 1M blended).
- GPT-5-Codex (high) streams 3.7× faster (195 vs 53 tokens per second).
At a glance
| Spec | Claude Fable 5 | GPT-5-Codex |
|---|---|---|
| Developer | Anthropic | OpenAI |
| Released | 9 Jun 2026 | 15 Sept 2025 |
| Context window (tokens) | 1,000,000 | 400,000 |
| Compared at | Claude Fable 5 | GPT-5-Codex (high) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $10.00 / $50.00 / $1.00 | $1.25 / $10.00 / $0.125 |
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 | Claude Fable 5 | GPT-5-Codex (high) | Leader |
|---|---|---|---|
| Reasoning | 80.0 | – | not comparable |
| Coding | 70.4 | 58.5 | Claude Fable 5 |
| Agents & tools | 64.2 | 66.8 | GPT-5-Codex |
| Knowledge | 66.5 | – | not comparable |
| Instruction following | – | 72.4 | not comparable |
| Human preference | 67.7 | – | not comparable |
| Multimodal | – | 56.4 | not comparable |
| Long context | – | 60.5 | not comparable |
Where sources disagree
Across the 1 benchmarks both have, Claude Fable 5 leads 1, GPT-5-Codex leads 0. Every overall index that rates both puts Claude Fable 5 ahead.
| Overall index | Claude Fable 5 | GPT-5-Codex (high) | Leader |
|---|---|---|---|
| BenchLeader Index | 66.6 | 58.6 | Claude Fable 5 |
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 | Claude Fable 5 | GPT-5-Codex (high) |
|---|---|---|
| Blended price per 1M tokens | $20.00 | $3.44 |
| Input / output per 1M | $10.00 / $50.00 | $1.25 / $10.00 |
| Cached input per 1M | $1.00 | $0.125 |
| Price per task: chat reply | $0.019 | $0.0035 |
| Price per task: summarize a 30-page report | $0.150 | $0.021 |
| Price per task: code edit | $0.135 | $0.022 |
| Price per task: agentic coding session | $0.800 | $0.115 |
| Price per task: structured extraction | $0.030 | $0.0045 |
| Output speed | 53 tok/s | 195 tok/s |
| Time to first answer | 3.8 s | 10.9 s |
| Time to a complete answer | – | 13.4 s |
Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5 scores 66.6 and takes 4 s to its first answer token; Claude Fable 5 (max) scores 65.3 in 70 s, Claude Fable 5 (high) scores 64.5 in 4 s. GPT-5-Codex (high) scores 58.6 and takes 11 s to its first answer token. 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
113 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 | Claude Fable 5 | GPT-5-Codex (high) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 66.6 | 58.6 |
| Agents & tools score | BenchLeader | 64.2 | 66.8 |
| Coding score | BenchLeader | 70.4 | 58.5 |
| Human preference score | BenchLeader | 67.7 | – |
| Knowledge score | BenchLeader | 66.5 | – |
| Reasoning score | BenchLeader | 80.0 | – |
| Instruction following score | BenchLeader | – | 72.4 |
| Long context score | BenchLeader | – | 60.5 |
| Multimodal score | BenchLeader | – | 56.4 |
| Blended price $/M | BenchLeader | $20.00 | $3.44 |
| Output speed | BenchLeader | 53 tok/s | 195 tok/s |
| Time to first answer | BenchLeader | 3.8 s | 10.9 s |
| Context window | BenchLeader | 1,000,000 tokens | 400,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 85.9%† | – |
| SimpleBench | SimpleBench | 81.9%† | – |
| Arena Hard Prompts | Arena (LMArena) | 1529† | – |
| LiveBench 1.0 Reasoning | LiveBench | 89.7%† | – |
| GPQA Diamond (AA) | Artificial Analysis | 92.6%† | 83.7% |
| Humanity's Last Exam (AA) | Artificial Analysis | 55.5%† | 27.9% |
| GPQA Diamond (Vals) | Vals AI | 93.2% | – |
| EnigmaEval | Scale AI SEAL | 39.3%† | – |
| Kagi LLM Benchmark | Kagi LLM Benchmark | 88.8% | 70.3%† |
| ARC-AGI-1 | ARC Prize | 98.5%† | – |
| ARC-AGI-2 | ARC Prize | 89.2%† | – |
| CritPt | Artificial Analysis | 28.6%† | 5.1% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 47.0%† | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 52.0%† | – |
| LMCA | Epoch AI Benchmarking Hub | 60.3%† | – |
| DTBench | Epoch AI Benchmarking Hub | 98.4%† | – |
| ForecastBench | ForecastBench | 66.0%† | – |
| BTF-3 | Epoch AI Benchmarking Hub | 13.0%† | – |
| Coding | |||
| SciCode | SciCode | 61.0%† | – |
| WeirdML | WeirdML | 91.9%† | 54.5% |
| FrontierCode | Cognition | 53.5% | – |
| GSO-Bench | GSO-Bench | 78.4% | – |
| Arena Coding | Arena (LMArena) | 1550† | – |
| Arena WebDev | Arena (LMArena) | 1624† | – |
| LiveBench 1.0 Coding | LiveBench | 86.0%† | – |
Show all 113 benchmarks
| Metric | Publisher | Claude Fable 5 | GPT-5-Codex (high) |
|---|---|---|---|
| Coding | |||
| LiveCodeBench | Vals AI | 89.8% | 84.7% |
| SWE-bench (Vals) | Vals AI | 95.0% | – |
| Code Migration | Vals AI | 55.1% | – |
| ProgramBench | Vals AI | 2.0% | – |
| Vibe Code Bench v1.1 | Vals AI | 90.3% | – |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 39.0%† | – |
| SWE Atlas: Refactoring | Scale AI SEAL | 54.8%† | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 55.6%† | – |
| MirrorCode | Epoch AI Benchmarking Hub | 63.9%† | – |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 95.0%† | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 69.7%† | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 2041.3† | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 47.0%† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 42.4%† | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 84.6%† | – |
| Startrise Frontend | Startrise | 73.8% | – |
| LiveCodeBench (AA) | Artificial Analysis | – | 84.0% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 44.5%† | 44.3%† |
| Remote Labor Index | Scale AI / CAIS | 16.1% | – |
| APEX-Agents | Mercor | 63.6% | – |
| Arena Agent | Arena (LMArena) | 8† | – |
| LiveBench Agentic Coding | LiveBench | 62.2%† | – |
| Terminal-Bench Hard | Artificial Analysis | 62.9%† | 37.9% |
| τ²-Bench Telecom (AA) | Artificial Analysis | 98.5%† | 86.8% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 80.5% | – |
| MCP Atlas | Scale AI SEAL | 83.3% | – |
| HiL-Bench | Scale AI SEAL | 56.3% | – |
| τ³-bench Banking | τ²-bench | 39.7%† | – |
| τ³-Banking (AA) | Artificial Analysis | 38.1%† | – |
| Analyst Agent (AA) | Artificial Analysis | 48.8%† | – |
| Finance Agent v2 | Vals AI | 56.3% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 11.3% | – |
| Legal Research Bench | Vals AI | 49.5% | – |
| Tax Agent Bench | Vals AI | 38.3% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 41.4% | – |
| Terminal-Bench Science | Vals AI | 15.7% | – |
| Web Search Index | Vals AI | 46.9% | – |
| Arena Search | Arena (LMArena) | 1229† | – |
| PostTrainBench | Epoch AI Benchmarking Hub | 41.8%† | – |
| GBAEval | Epoch AI Benchmarking Hub | 74.5% | – |
| Vending-Bench 2 | Andon Labs | 4529.9 | – |
| AutomationBench | Artificial Analysis | 54.1%† | – |
| GDP.pdf (AA) | Artificial Analysis | 24.0%† | – |
| EnterpriseOps-Gym | Artificial Analysis | 51.1%† | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1535† | – |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 87.0%† | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 90.2%† | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 99.7%† | – |
| ProofBench | Vals AI | 95.0%† | – |
| LiveBench Mathematics | LiveBench | 96.0%† | – |
| Arena Maths | Arena (LMArena) | 1521† | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 70.7%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 80.5%† | – |
| MMLU-Pro | Vals AI | 91.5% | – |
| LegalBench | Vals AI | 88.6% | – |
| CorpFin | Vals AI | 71.8% | – |
| TaxEval | Vals AI | 76.9% | – |
| PRBench Finance | Scale AI SEAL | 53.9% | – |
| PRBench Legal | Scale AI SEAL | 52.6% | – |
| Excel Modeling Benchmark | Vals AI | 73.7% | – |
| MedCode | Vals AI | 56.1% | – |
| MedScribe | Vals AI | 88.5% | – |
| Public Benefits Bench v1.1 | Vals AI | 70.4% | – |
| EBR-bench | Epoch AI Benchmarking Hub | 39.5%† | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 30.0% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 90.7%† | – |
| LiveBench Instruction Following | LiveBench | 75.8%† | – |
| IFBench | Artificial Analysis | 63.5%† | 74.2% |
| Arena Instruction Following | Arena (LMArena) | 1509† | – |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1504† | – |
| EQ-Bench 4 | EQ-Bench | 1313 | – |
| Arena Creative Writing | Arena (LMArena) | 1501† | – |
| Arena Multi-turn | Arena (LMArena) | 1516† | – |
| Arena Longer Queries | Arena (LMArena) | 1522† | – |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1325† | – |
| MMMU-Pro | Artificial Analysis | – | 73.8% |
| MMMU-Pro (Vals) | Vals AI | 89.3% | – |
| MortgageTax | Vals AI | 68.9% | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 38.6% | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.3%† | 71.7% |
| Arena Document | Arena (LMArena) | 1499 | – |
| MLCR | Artificial Analysis | 20.6%† | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 163.1 | – |
| LiveBench 1.0 | LiveBench | 83.0%† | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 49.6† | 24.9 |
| AA Progress Index v1 | Artificial Analysis | 329.3† | 275.1 |
| Vals RSI Index | Vals AI | 24.3%† | – |
| Vals Multimodal Index | Vals AI | 74.2% | – |
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 (LiveCodeBench (AA)).
- GPT-5-Codex (high): 1 new result (AA Progress Index v1).
- Claude Fable 5: BenchLeader Index 67.3 → 66.5.
- Claude Fable 5: 1 score revision.
- Claude Fable 5: 1 new result (Harvey's Legal Agent Benchmark v1).
- Claude Fable 5: 1 score revision.
- GPT-5-Codex (high): BenchLeader Index 59.0 → 58.5.
- Claude Fable 5: 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
- Claude Fable 5: 1 new result (Startrise Frontend); 1 score revision.
- Claude Fable 5: BenchLeader Index 67.8 → 67.3.
Related comparisons
- Claude Fable 5 vs Claude Opus 5.5
- Claude Fable 5 vs Gemini 4 Carbon
- Claude Fable 5 vs GPT-6 Astra
- GPT-5-Codex vs Claude Opus 5.5
- GPT-5-Codex vs Gemini 4 Carbon
- GPT-5-Codex vs GPT-6 Astra
- GPT-5-Codex vs GPT-6.1 Sol
- Claude Fable 5 vs GPT-5 Pro
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Fable 5 vs GPT-5-Codex: questions
- Is Claude Fable 5 better than GPT-5-Codex?
- Claude Fable 5 leads on quality: 66.6 vs 58.6. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5 is ahead overall as of 29 Oct 2026, but check the category scores for your use.
- Claude Fable 5 vs GPT-5-Codex: which is cheaper, and will that change?
- GPT-5-Codex is cheaper today: $3.44 against $20.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Claude Fable 5 or GPT-5-Codex better for coding?
- Claude Fable 5 scores higher in coding (70 vs 59 on the category index, where 50 is average). On LiveCodeBench, the top shared coding benchmark, it is 89.8% for Claude Fable 5 against 84.7% for GPT-5-Codex.
- Which is faster, Claude Fable 5 or GPT-5-Codex?
- GPT-5-Codex streams 3×+ faster (195 vs 53 output tokens per second, Artificial Analysis 7-day median).
- Is Claude Fable 5 or GPT-5-Codex 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?
- Claude Fable 5 accepts more context: 1,000,000 against 400,000 tokens for GPT-5-Codex.
- Which has lower latency?
- Claude Fable 5 answers first: 3.8 s against 10.9 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 Claude Fable 5 vs GPT-5-Codex?
- Across the 1 benchmarks both have, Claude Fable 5 leads 1, GPT-5-Codex leads 0. Every overall index that rates both puts Claude Fable 5 ahead.
- When was Claude Fable 5 released?
- Claude Fable 5 was released on 9 Jun 2026.