text model comparison
Claude Sonnet 5.5 vs GPT-5.4
Claude Sonnet 5.5 and GPT-5.4 are both current text models, from Anthropic and OpenAI. Claude Sonnet 5.5 is 20% cheaper per 1M input tokens than GPT-5.4, $2 vs $2.50. On Arena Text, Claude Sonnet 5.5 scores 1477 Elo and GPT-5.4 1475 Elo (Arena, measured October 28, 2026). GPT-5.4 has the larger context window, 1,050,000 vs 1,000,000 tokens.
- Higher Arena Text
- Claude Sonnet 5.51477 Elo against 1475 Elo
- Lower price per 1M input tokens
- Claude Sonnet 5.5$2 against $2.50
- Longer context window
- GPT-5.41.05M tokens against 1M tokens
- Newer release
- Claude Sonnet 5.5Sep 2026 against Mar 2026
Data verified November 3, 2026 · Dataset 2026-11-06
Side by side
Claude Sonnet 5.5 and GPT-5.4, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | Claude Sonnet 5.5 | GPT-5.4 |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $2 (better) | $2.50 |
| Price per 1M output tokens | $10 (better) | $15 |
| Independent benchmarks | ||
| Arena Text | 1477 Elo (#20 of 52) (better) | 1475 Elo (#24 of 52) |
| Arena WebDev | 1770 Elo (#3 of 46) (better) | 1401 Elo (#41 of 46) |
| GPQA Diamond | 95.6% (#3 of 41) (better) | 93.3% (#14 of 41) |
| FrontierMath Tiers 1-3 (v2) | 88.8% (#8 of 41) (better) | 78.6% (#18 of 41) |
| SimpleQA Verified | 46.5% (#23 of 38) (better) | 45.1% (#25 of 38) |
| LiveBench Overall | Not measured | 77.97 points (#3 of 4) |
| Specs | ||
| Provider | Anthropic | OpenAI |
| Release date | September 28, 2026 | March 5, 2026 |
| Access | API only | API only |
| Context window | 1,000,000 tokens | 1,050,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Input | text, image | text, image |
| Output | text | text |
Scores:Arena · 2026-11-03Epoch AI · 2026-11-03LiveBench · 2026-06-25
Charts
Against every current text model
Where Claude Sonnet 5.5 and GPT-5.4 land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
On Arena Text, Claude Sonnet 5.5 ranks #20 and GPT-5.4 #24 of 52 current models. Each bar is the share of current models it beats: on score, price and context.
Independent benchmarks
Arena Text
Claude Sonnet 5.5:#20of 52
1,477 Elo · ahead of 61%
GPT-5.4:#24of 52
1,475 Elo · ahead of 55%
Arena WebDev
Claude Sonnet 5.5:#3of 46
1,770 Elo · ahead of 96%
GPT-5.4:#41of 46
1,401 Elo · ahead of 11%
GPQA Diamond
Claude Sonnet 5.5:#3of 41
95.6% · ahead of 95%
GPT-5.4:#14of 41
93.3% · ahead of 65%
FrontierMath Tiers 1-3 (v2)
Claude Sonnet 5.5:#8of 41
88.8% · ahead of 83%
GPT-5.4:#18of 41
78.6% · ahead of 57%
SimpleQA Verified
Claude Sonnet 5.5:#23of 38
46.5% · ahead of 41%
GPT-5.4:#25of 38
45.1% · ahead of 35%
Price and context
Price per 1M input tokens
Claude Sonnet 5.5:#31of 58
$2 · cheaper than 26%
GPT-5.4:#44of 58
$2.50 · cheaper than 25%
Price per 1M output tokens
Claude Sonnet 5.5:#36of 58
$10 · cheaper than 28%
GPT-5.4:#44of 58
$15 · cheaper than 23%
Context window
Claude Sonnet 5.5:#27of 67
1M tokens · longer than 24%
GPT-5.4:#1of 67
1.05M tokens · longer than 85%
Quality against price
Claude Sonnet 5.5 scores 1,477 at $4; GPT-5.4 scores 1,475 at $5.63 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.
Quality against price: the data
| Model | Provider | Blended price per 1M tokens | Arena Text (Elo) |
|---|---|---|---|
| Gemini 4 Carbon | $4 | 1,528 | |
| Gemini 4 Argon | $4 | 1,520 | |
| Claude Opus 5.5 | Anthropic | $8 | 1,509 |
| Muse Wonder | Meta | $8 | 1,507 |
| Claude Fable 5 | Anthropic | $20 | 1,504 |
| Claude Fable 5.1 | Anthropic | $20 | 1,504 |
| Gemini 3.8 Flash | $1.50 | 1,496 | |
| Muse Spark 1.3 | Meta | $2 | 1,495 |
| Claude Opus 5 | Anthropic | $10 | 1,492 |
| Kimi K3 | Moonshot Kimi | $6 | 1,488 |
| GPT-5.6 Sol | OpenAI | $8 | 1,485 |
| Gemini 3.6 Flash | $3 | 1,483 | |
| GPT-5.5 | OpenAI | $11 | 1,482 |
| Claude Opus 4.8 | Anthropic | $10 | 1,482 |
| Qwen3.8-Max | Alibaba Qwen | $3 | 1,482 |
| GPT-6.1 Sol | OpenAI | $4 | 1,481 |
| GLM-5.3 | Z.ai | $2.15 | 1,481 |
| MiMo-V2.6-Pro | Xiaomi MiMo | $0.54 | 1,480 |
| Claude Sonnet 5.5 | Anthropic | $4 | 1,477 |
| GLM-5.3-Flash | Z.ai | $0.24 | 1,477 |
| GPT-6 Astra | OpenAI | $20 | 1,476 |
| DeepSeek-V4.1-Flash | DeepSeek | $0.52 | 1,476 |
| GPT-5.4 | OpenAI | $5.63 | 1,475 |
| Gemini 3 Flash Preview | $1.13 | 1,473 | |
| Grok 4.20 | xAI | $1.56 | 1,472 |
| GPT-5.6 Terra | OpenAI | $4.50 | 1,467 |
| Grok 4.5 | xAI | $3 | 1,465 |
| DeepSeek-V4-Pro | DeepSeek | $1.98 | 1,465 |
| Claude Sonnet 5 | Anthropic | $4 | 1,462 |
| GPT-6 Sol | OpenAI | $4 | 1,458 |
| Gemini 3.5 Flash-Lite | $0.85 | 1,456 | |
| Grok 4.6 | xAI | $3 | 1,455 |
| GPT-5.6 Luna | OpenAI | $0.45 | 1,453 |
| MiMo-V2.6-Flash | Xiaomi MiMo | $0.18 | 1,448 |
| Step 5 Preview | StepFun | $1.43 | 1,448 |
| Grok 4.3 | xAI | $1.56 | 1,442 |
| GPT-6 Luna | OpenAI | $0.20 | 1,441 |
| Grok 4.7 | xAI | $3 | 1,441 |
| Mistral Large 4 | Mistral AI | $1.05 | 1,432 |
| Claude Haiku 5.5 | Anthropic | $0.20 | 1,425 |
| GPT-4.1 | OpenAI | $3.50 | 1,415 |
| Solar Pro 4 | Upstage | $0.52 | 1,388 |
| GPT-4.1 mini | OpenAI | $0.70 | 1,383 |
| GPT-4.1 nano | OpenAI | $0.18 | 1,322 |
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
For 10M input and 2M output tokens, GPT-5.4 costs 1.4 times as much as Claude Sonnet 5.5, at each provider's listed rates.
10M input and 2M output tokens
GPT-5.4 costs 1.4× as much
- Claude Sonnet 5.5
- $40
- GPT-5.4
- $55
The same, with 9M of the input tokens cached
GPT-5.4 costs 1.5× as much
- Claude Sonnet 5.5
- $22.90
- GPT-5.4
- $34.75
| Workload or rate | Claude Sonnet 5.5 | GPT-5.4 |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $40 (better) | $55 |
| The same, with 9M of the input tokens cached | $22.90 (better) | $34.75 |
| The same, through the batch API | $20 | Not listed |
| Other listed rates | ||
| 1M input tokens, cached | $0.10 (better) | $0.25 |
| 1M input tokens, 5-minute cache write | $2.50 | Not listed |
| 1M input tokens, 1-hour cache write | $4 | Not listed |
| 1M input tokens, batch | $1 | Not listed |
| 1M output tokens, batch | $5 | Not listed |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
Claude Sonnet 5.5
Where it leads
- Lower input and output prices, $2 and $10 vs $2.50 and $15 per 1M tokens
- Higher Arena Text score, 1477 Elo vs 1475 Elo
- Higher Arena WebDev score, 1770 Elo vs 1401 Elo
- Higher GPQA Diamond score, 95.6% vs 93.3%
- Higher FrontierMath Tiers 1-3 (v2) score, 88.8% vs 78.6%
- Higher SimpleQA Verified score, 46.5% vs 45.1%
- Cheaper cached input, $0.10 vs $0.25 per 1M tokens
- Batch pricing, $1 input and $5 output per 1M tokens
Best for
- Production workloads that need frontier-adjacent quality at a mid-tier rate
- Latency-sensitive agent steps inside a larger pipeline
Watch out for
- Same list price as Claude Sonnet 5, so the gain is capability and cache economics rather than a cheaper rate card
- Anthropic positions Opus 5.5 rather than this as the default, so reach for Sonnet 5.5 when latency matters more than peak capability
GPT-5.4
Where it leads
- Larger context window 1,050,000 vs 1,000,000 tokens
Best for
- Long-context coding and professional-work evaluations
Watch out for
- Prompts above the provider long-context threshold use higher token rates; reproduce cost and quality on the target workload
From benchmark to production
Building on Claude Sonnet 5.5 or GPT-5.4?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
AI Model Cost AuditLaunch price $100, regular price $150What the audit includes
FAQ
Claude Sonnet 5.5 vs GPT-5.4 FAQ
Which is cheaper, Claude Sonnet 5.5 or GPT-5.4?
Claude Sonnet 5.5 is 20% cheaper per 1M input tokens than GPT-5.4, $2 vs $2.50. For 10M input and 2M output tokens, Claude Sonnet 5.5 costs $40 and GPT-5.4 $55 at standard rates.
Which is cheaper with prompt caching, Claude Sonnet 5.5 or GPT-5.4?
Claude Sonnet 5.5 charges $0.10 per 1M cached input tokens, 95% below its standard input rate, and GPT-5.4 $0.25, 90% below. With 9M of 10M input tokens cached and 2M output tokens, Claude Sonnet 5.5 costs $22.90 and GPT-5.4 $34.75.
Which scores higher on independent benchmarks, Claude Sonnet 5.5 or GPT-5.4?
Claude Sonnet 5.5 leads on Arena Text, 1477 Elo to 1475 Elo; Claude Sonnet 5.5 leads on Arena WebDev, 1770 Elo to 1401 Elo; Claude Sonnet 5.5 leads on GPQA Diamond, 95.6% to 93.3%. Scores are independent evaluations, not either vendor's launch figures.
Which has the larger context window, Claude Sonnet 5.5 or GPT-5.4?
GPT-5.4 has the larger context window, 1,050,000 vs 1,000,000 tokens. Both return up to 128,000 tokens per response.
Further reading
More on Claude Sonnet 5.5 and GPT-5.4
Articles on Claude Sonnet 5.5 and GPT-5.4
- Claude Sonnet 5.5 vs GPT-6 Luna: Cost, Speed and AccuracySeptember 29, 2026
- Claude Sonnet 5.5: Benchmarks, Price and When to Use OpusSeptember 29, 2026
- GPT-5.4 vs Claude Opus 4.7: Which Model for Production AI Agents?April 16, 2026
Related comparisons
- Claude Haiku 5.5 vs Claude Sonnet 5.5
- Claude Sonnet 5 vs GPT-5.4
- Claude Sonnet 5.5 vs Gemini 4 Argon
- GPT-5.4 vs GPT-6 Luna
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- DeepSeek-V4.1-Flash vs GPT-5.4
- Claude Opus 4.8 vs Claude Sonnet 5.5
- GPT-5.4 vs Kimi K3
- Claude Opus 5.5 vs Claude Sonnet 5.5
- Gemini 3.1 Pro Preview vs GPT-5.4
- Claude Opus 5 vs Claude Sonnet 5.5
- GLM-5.3-Flash vs GPT-5.4
Production evaluation
Choosing between Claude Sonnet 5.5 and GPT-5.4?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty
