readable AI benchmarks (simplified)
Anthropic
Claude Opus 5 (Max)
Claude Opus 5 (Max) has a Quality Score of 73.3, ranking 18th among 571 scored models. Per 1M tokens, pricing is $5.00 input, $25.00 output, $0.500 cached input, and $6.25 cache write. It accepts text, image, and pdf input, outputs text, and has a 1M token context window. Its Reliability Score is 68.5, ranking 22nd among 573 scored models, above average (total average: 36.5). Its Value Score is 43.7, 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
- $5.00
- Output
- $25.00
- Cached Input
- $0.500
- Cache write
- $6.25
- Cost per task
- $5.86
Capability
- Intelligence
- 50.8
- Coding
- not available
- Agentic
- not available
- Omniscience
- 37.1
- Correct
- 60.9%
- Blended price
- $3.85
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 84.7%
Artificial Analysis benchmarks
- GDPval-AA v2
- 61%
- τ³-Banking
- 42%
- SciCode
- 56%
- Humanity’s Last Exam
- 55%
- GPQA Diamond
- 93%
- CritPt
- 29%
- AA-Omniscience
- 69%
- AA-LCR
- 79%
DeepSWE operational cross-check
- Pass@1
- 73.6%
- Avg steps/scored attempt
- 99.04
- Mean cost/scored attempt (USD)
- $11.84
- Mean output tokens/scored attempt
- 117,565.694
- Mean duration/scored attempt (s)
- 1912 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 Fable 5 (Max, Opus 4.8 Fallback)AnthropicQuality Score 74.0Value Score 40.9
- Claude Fable 5.1 (High, Default Fallback)AnthropicQuality Score 74.5Value Score 41.5
- Claude Opus 5.5 (Medium, Default Fallback)AnthropicQuality Score 74.5Value Score 45.8
- Claude Opus 5 (Xhigh)AnthropicQuality Score 72.1Value Score 43.0
- Claude Fable 5.1 (Medium, Default Fallback)AnthropicQuality Score 72.0Value Score 40.1
- Claude Sonnet 5.5 (Xhigh, Default Fallback)AnthropicQuality Score 70.8Value Score 47.0