Claude Fable 5.2 vs Gemini 4 Hydrogen
Full profiles: Claude Fable 5.2 (Anthropic) and Gemini 4 Hydrogen (Google): every benchmark, price and rank.
Updated · Data from 10 sources
As of 13 Nov 2026, Claude Fable 5.2 is ahead of Gemini 4 Hydrogen on quality (72.7 vs 63.4 on the BenchLeader Index), but Gemini 4 Hydrogen is 5.3× cheaper at $3.00 vs $16.00 per 1M tokens blended. Claude Fable 5.2 leads in every category we measure both in. Gemini 4 Hydrogen streams ~1.5× faster.
Key facts (as of 13 Nov 2026)
- Claude Fable 5.2 scores 72.7 on the BenchLeader Index and Gemini 4 Hydrogen scores 63.4 (BenchLeader, 13 Nov 2026).
- Claude Fable 5.2 costs $16.00 per 1M tokens blended (list price, 13 Nov 2026).
- Gemini 4 Hydrogen costs $3.00 per 1M tokens blended (list price, 13 Nov 2026).
- Gemini 4 Hydrogen streams ~1.5× faster than Claude Fable 5.2 (Artificial Analysis, 7-day median, 13 Nov 2026).
- Of the 12 benchmarks both models have, Claude Fable 5.2 leads 10 (BenchLeader, 13 Nov 2026).
Claude Fable 5.2 benchmarks 
Gemini 4 Hydrogen 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 5.2 | 80 vs 69 category score; FrontierCode 2.0 (AA) 48.8% vs 36.3% | High |
| Agents & tool use | Claude Fable 5.2 | 78 vs 62 category score; Terminal-Bench 65.8% vs 56.4% | High |
| Maths | Claude Fable 5.2 | 75 vs 68 category score | Medium |
| Reasoning | Claude Fable 5.2 | 76 vs 70 category score; HLE-Diamond (AA) 80.2% vs 54.9% | Medium |
| Knowledge | Claude Fable 5.2 | 86 vs 69 category score; AA-Omniscience v1.1 66.8 vs 43.7 | High |
| Chat quality (human preference) | – | Only Gemini 4 Hydrogen has an Arena rating (68 category score) | Not comparable |
| Lowest cost | Gemini 4 Hydrogen | $3.00 vs $16.00 per 1M blended; agentic coding session $0.120 vs $0.640 | – |
| Fastest first answer | Gemini 4 Hydrogen | 16.4 s (Gemini 4 Hydrogen (high)) vs 259.3 s (Claude Fable 5.2 (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
- Claude Fable 5.2 (max) leads on quality: 72.7 vs 63.4.
- Claude Fable 5.2 (max) is stronger in agents & tools, coding, knowledge, maths, reasoning.
- Gemini 4 Hydrogen (high) is 5.3× cheaper ($3.00 vs $16.00 per 1M blended).
- Gemini 4 Hydrogen (high) streams 1.8× faster (180 vs 99 tokens per second).
At a glance
| Spec | Claude Fable 5.2 | Gemini 4 Hydrogen |
|---|---|---|
| Developer | Anthropic | |
| Released | 9 Nov 2026 | 12 Nov 2026 |
| Context window (tokens) | 1,000,000 | 1,048,576 |
| Compared at | Claude Fable 5.2 (max) | Gemini 4 Hydrogen (high) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $8.00 / $40.00 / $0.200 | $1.50 / $7.50 / $0.075 |
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 5.2 (max) | Gemini 4 Hydrogen (high) | Leader |
|---|---|---|---|
| Reasoning | 75.6 | 69.6 | Claude Fable 5.2 |
| Coding | 79.7 | 68.8 | Claude Fable 5.2 |
| Agents & tools | 77.5 | 61.9 | Claude Fable 5.2 |
| Maths | 74.5 | 67.8 | Claude Fable 5.2 |
| Knowledge | 86.3 | 68.5 | Claude Fable 5.2 |
| Human preference | – | 68.2 | not comparable |
| Long context | 66.4 | – | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 12 benchmarks both have, Claude Fable 5.2 leads 10, Gemini 4 Hydrogen leads 2. Every overall index that rates both puts Claude Fable 5.2 ahead.
| Overall index | Claude Fable 5.2 (max) | Gemini 4 Hydrogen (high) | Leader |
|---|---|---|---|
| BenchLeader Index | 72.7 | 63.4 | Claude Fable 5.2 |
| AA Intelligence Index v5.0 | 64.6 | 50.8 | Claude Fable 5.2 |
| Vals Index | 71.3† | 68.5 | Claude Fable 5.2 |
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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Claude Fable 5.2 (max) | Gemini 4 Hydrogen (high) |
|---|---|---|
| Blended price per 1M tokens | $16.00 | $3.00 |
| Input / output per 1M | $8.00 / $40.00 | $1.50 / $7.50 |
| Cached input per 1M | $0.200 | $0.075 |
| Price per task: chat reply | $0.015 | $0.0029 |
| Price per task: summarize a 30-page report | $0.120 | $0.022 |
| Price per task: code edit | $0.108 | $0.020 |
| Price per task: agentic coding session | $0.640 | $0.120 |
| Price per task: structured extraction | $0.024 | $0.0045 |
| Agentic coding session, input mostly cached | $0.289 | $0.056 |
| Cost per benchmark task (AA Index) | $26.54 | $1.87 |
| Output tokens per task (AA Index) | 274k | 85k |
| Of which reasoning | 193k | 48k |
| Time per task (AA Index) | 46 min | 8 min |
| Output speed | 99 tok/s | 180 tok/s |
| Time to first answer | 259.3 s | 16.4 s |
| Time to a complete answer | 456.8 s | 63.3 s |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $26.54 on Claude Fable 5.2 (max) and $1.87 on Gemini 4 Hydrogen (high), and Claude Fable 5.2 (max) wrote 3.2× as many output tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5.2 (max) scores 72.7 and takes 259 s to its first answer token; Claude Fable 5.2 (xhigh) scores 69.9 in 87 s, Claude Fable 5.2 (high) scores 68.4 in 29 s. Gemini 4 Hydrogen (high) scores 63.4 and takes 16 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
87 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 5.2 (max) | Gemini 4 Hydrogen (high) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 72.7 | 63.4 |
| Agents & tools score | BenchLeader | 77.5 | 61.9 |
| Coding score | BenchLeader | 79.7 | 68.8 |
| Knowledge score | BenchLeader | 86.3 | 68.5 |
| Long context score | BenchLeader | 66.4 | – |
| Maths score | BenchLeader | 74.5 | 67.8 |
| Reasoning score | BenchLeader | 75.6 | 69.6 |
| Human preference score | BenchLeader | – | 68.2 |
| Blended price $/M | BenchLeader | $16.00 | $3.00 |
| Output speed | BenchLeader | 99 tok/s | 180 tok/s |
| Time to first answer | BenchLeader | 259.3 s | 16.4 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 93.9% | – |
| SimpleBench | SimpleBench | 94.9%† | – |
| Arena Hard Prompts | Arena (LMArena) | – | 1514 |
| LiveBench 2.0 Reasoning | LiveBench | 88.8%† | 88.6%† |
| Humanity's Last Exam (AA) | Artificial Analysis | 74.3% | – |
| HLE-Diamond (AA) | Artificial Analysis | 80.2% | 54.9% |
| ARC-AGI-1 | ARC Prize | 97.5% | – |
| ARC-AGI-2 | ARC Prize | 92.5% | – |
| ARC-AGI-3 | ARC Prize | 94.9% | – |
| CritPt | Artificial Analysis | 35.4% | – |
| CritPt v2 hard subset (AA) | Artificial Analysis | 76.5% | 61.5% |
| MysteryMechanism | Vals AI | 51.8%† | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 79.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 90.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 70.1%† | – |
| DTBench | Epoch AI Benchmarking Hub | 99.2%† | – |
| Coding | |||
| SciCode | SciCode | 67.7% | – |
| Arena Coding | Arena (LMArena) | – | 1518 |
| Arena WebDev | Arena (LMArena) | 1838† | 1704 |
| LiveBench 2.0 Coding | LiveBench | 79.2%† | 78.5%† |
| Code Migration v1.1 | Vals AI | 83.3%† | – |
| ProgramBench | Vals AI | 19.0%† | – |
| SWE-bench Multimodal | Vals AI | 62.3%† | – |
| Vibe Code Bench v1.1 | Vals AI | 93.8%† | 87.8%† |
| CursorBench | Cursor | 60.0% | – |
Show all 87 benchmarks
| Metric | Publisher | Claude Fable 5.2 (max) | Gemini 4 Hydrogen (high) |
|---|---|---|---|
| Coding | |||
| ALE-Bench | Epoch AI Benchmarking Hub | 2509.8† | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 69.9% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 59.6% | 54.0% |
| Design Arena Website | Design Arena | 1352† | 1316† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 56.2% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 48.8% | 36.3% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 65.8% | 56.4% |
| Remote Labor Index | Scale AI / CAIS | 41.3%† | – |
| APEX-Agents | Mercor | 80.1%† | – |
| Arena Agent | Arena (LMArena) | 30.4 | – |
| LiveBench Long Agentic | LiveBench | 82.9%† | 61.8%† |
| LiveBench Browser | LiveBench | 86.9%† | 77.1%† |
| HiL-Bench | Scale AI SEAL | 80.0%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 1831 | – |
| Finance Agent v2.1 | Vals AI | 69.5%† | 65.1%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 5.0%† | 11.3%† |
| Legal Research Bench | Vals AI | 46.1%† | 53.9%† |
| Tax Agent Bench | Vals AI | 32.1%† | 52.3%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 65.2%† | 54.0%† |
| Terminal-Bench Science | Vals AI | 55.7%† | – |
| AutomationBench | Artificial Analysis | 76.4% | 74.4% |
| GDP.pdf (AA) | Artificial Analysis | 24.2% | 30.0% |
| Harvey LAB-AA v1.1 | Harvey | 7.2% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1785 | 1497 |
| GDPx | GDPx by SemiAnalysis | 16.4% | – |
| Design Arena Agentic | Design Arena | 1368† | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 73.3% | 41.4% |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 95.1% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 100.0% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 99.7% | – |
| ProofBench | Vals AI | 100.0% | – |
| Arena Maths | Arena (LMArena) | – | 1495 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 94.0% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 81.5%† | 83.2%† |
| LiveBench Research | LiveBench | 94.5%† | 86.8%† |
| AA-Omniscience v1.1 | Artificial Analysis | 66.8 | 43.7 |
| PRBench Finance | Scale AI SEAL | 47.1%† | – |
| PRBench Legal | Scale AI SEAL | 49.0%† | – |
| BioMysteryBench | Vals AI | 83.7%† | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 77.4%† | 75.8%† |
| EBR-bench | Epoch AI Benchmarking Hub | 90.5% | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 79.1% | 48.2% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 40.7% | 91.3% |
| HealthBench Professional (AA) | OpenAI | 67.7% | – |
| Instruction following | |||
| Arena Instruction Following | Arena (LMArena) | – | 1503 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1490 |
| Arena Creative Writing | Arena (LMArena) | – | 1492 |
| Arena Multi-turn | Arena (LMArena) | – | 1476 |
| Arena Longer Queries | Arena (LMArena) | – | 1514 |
| Multimodal | |||
| LiveBench Design | LiveBench | 85.1%† | 77.3%† |
| AA-3D | Artificial Analysis | 1271 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 83.3% | – |
| MLCR | Artificial Analysis | 43.9% | 21.1%† |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 173.4† | – |
| LiveBench 2.0 | LiveBench | 84.9%† | 77.0%† |
| AA Intelligence Index v5.0 | Artificial Analysis | 64.6 | 50.8 |
| AA Progress Index v1 | Artificial Analysis | 358 | – |
| Vals Index | Vals AI | 71.3† | 68.5† |
| Vals Finance Index | Vals AI | 63.6%† | 66.1%† |
| Vals RSI Index | Vals AI | 37.9% | – |
| Vals Science Index | Vals AI | 63.7%† | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 15.6%† | – |
Data as of 2026-11-13. Best configuration of each model; every score links to its source on the model pages.
What changed
- Claude Fable 5.2 (max): BenchLeader Index 74.9 → 72.7.
- Claude Fable 5.2 (max): 1 new result (Terminal-Bench).
- Gemini 4 Hydrogen (high): 10 new results (Arena Text, Arena Hard Prompts, Arena Coding…).
- Claude Fable 5.2 (max): BenchLeader Index 72.1 → 74.9.
- Claude Fable 5.2 (max): 1 new result (Arena Agent).
- Claude Fable 5.2 (max): 3 new results (SciCode, CursorBench, FrontierSWE).
- Claude Fable 5.2 (max): BenchLeader Index 69.4 → 72.1.
- Claude Fable 5.2 (max): 13 new results (GPQA Diamond, FrontierMath Tiers 1–3, FrontierMath Tier 4…).
Related comparisons
- Claude Fable 5.2 vs Gemini 4 Carbon
- Claude Fable 5.2 vs Claude Opus 5.5
- Claude Fable 5.2 vs GPT-6 Astra
- Gemini 4 Hydrogen vs Gemini 4 Carbon
- Gemini 4 Hydrogen vs Claude Opus 5.5
- Gemini 4 Hydrogen vs GPT-6 Astra
- Claude Sonnet 5.5 vs Gemini 4 Hydrogen
- Claude Fable 5.2 vs GPT-6.1 Sol
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Fable 5.2 vs Gemini 4 Hydrogen: questions
- Is Claude Fable 5.2 better than Gemini 4 Hydrogen?
- Claude Fable 5.2 (max) leads on quality: 72.7 vs 63.4. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.2 (max) is ahead overall as of 13 Nov 2026, but check the category scores for your use.
- Claude Fable 5.2 vs Gemini 4 Hydrogen: which is cheaper, and will that change?
- Gemini 4 Hydrogen is cheaper today: $3.00 against $16.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Claude Fable 5.2 or Gemini 4 Hydrogen better for coding?
- Claude Fable 5.2 scores higher in coding (80 vs 69 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 48.8% for Claude Fable 5.2 against 36.3% for Gemini 4 Hydrogen.
- Which is faster, Claude Fable 5.2 or Gemini 4 Hydrogen?
- Gemini 4 Hydrogen streams ~1.5× faster (180 vs 99 output tokens per second, Artificial Analysis 7-day median).
- Is Claude Fable 5.2 or Gemini 4 Hydrogen better for agents and tool use?
- Claude Fable 5.2 scores higher in agentic tasks (78 vs 62 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 65.8% for Claude Fable 5.2 against 56.4% for Gemini 4 Hydrogen.
More questions (4)
- Which is better for long documents?
- Both take about 1M tokens: Claude Fable 5.2 1,000,000, Gemini 4 Hydrogen 1,048,576.
- Which has lower latency?
- Gemini 4 Hydrogen answers first: 16.4 s against 259.3 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 5.2 vs Gemini 4 Hydrogen?
- Across the 12 benchmarks both have, Claude Fable 5.2 leads 10, Gemini 4 Hydrogen leads 2. Every overall index that rates both puts Claude Fable 5.2 ahead.
- When was Gemini 4 Hydrogen released?
- Gemini 4 Hydrogen was released on 12 Nov 2026.