readable AI benchmarks (simplified)
Anthropic
Claude Sonnet 5 (Max)
Claude Sonnet 5 (Max) has a Quality Score of 58.5, ranking 65th among 571 scored models. Per 1M tokens, pricing is $2.00 input, $10.00 output, $0.200 cached input, and $2.50 cache write. It accepts text, image, and pdf input, outputs text, and has a 1M token context window. Its Reliability Score is 58.2, ranking 75th among 573 scored models, above average (total average: 36.5). Its Value Score is 38.8, high compared with the total Value average of 31.4.
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image, pdf
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $2.00
- Output
- $10.00
- Cached Input
- $0.200
- Cache write
- $2.50
- Cost per task
- $5.09
Capability
- Intelligence
- 38.2
- Coding
- not available
- Agentic
- not available
- Omniscience
- 16.4
- Correct
- 40.1%
- Blended price
- $1.54
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 63.7%
Artificial Analysis benchmarks
- GDPval-AA v2
- 48%
- τ³-Banking
- 37%
- SciCode
- 54%
- Humanity’s Last Exam
- 41%
- GPQA Diamond
- 91%
- CritPt
- 17%
- AA-Omniscience
- 58%
- AA-LCR
- 82%
DeepSWE operational cross-check
- Pass@1
- 53.8%
- Avg steps/scored attempt
- 268.45
- Mean cost/scored attempt (USD)
- $26.40
- Mean output tokens/scored attempt
- 214,117.55
- Mean duration/scored attempt (s)
- 4804 s
Mean cost/scored attempt is the official feed's mean_cost_usd: mean benchmark cost in USD per scored attempt under the source's cost basis. It is not Artificial Analysis cost per task and not token price (USD per 1M tokens). Mean output tokens/scored attempt is mean_output_tokens, also averaged over every scored attempt including scored failures. Mean duration/scored attempt is mean_duration_seconds; it is informational only, and wall-clock varies with provider and host load. These three fields do not affect Quality Score, Value Score, or Reliability. Epoch General ECI's benchmark basket includes DeepSWE v1.1, so Epoch General ECI and this DeepSWE cross-check are not independent evidence.
Similar models
- Claude Sonnet 5.5 (Low, Default Fallback)AnthropicQuality Score 57.4Value Score 38.1
- Claude Sonnet 5.5 (Medium, Default Fallback)AnthropicQuality Score 61.4Value Score 40.8
- Claude Opus 5 (Low)AnthropicQuality Score 62.4Value Score 37.2
- Claude Opus 4.7 (Max)AnthropicQuality Score 63.1Value Score 37.7
- Claude Opus 4.8 (Max)AnthropicQuality Score 64.3Value Score 38.4
- Claude Sonnet 5 (Xhigh)AnthropicQuality Score 52.2Value Score 34.7