readable AI benchmarks (simplified)
OpenAI
GPT-5.6 Terra (Medium)
GPT-5.6 Terra (Medium) has a Quality Score of 46.9, ranking 132nd among 571 scored models. Per 1M tokens, pricing is $2.00 input, $12.00 output, $0.200 cached input, and $2.50 cache write. It has a 1M token context window. Its Reliability Score is 47.4, ranking 156th among 573 scored models, above average (total average: 36.5). Its Value Score is 30.7, around average compared with the total Value average of 31.4.
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $2.00
- Output
- $12.00
- Cached Input
- $0.200
- Cache write
- $2.50
- Cost per task
- $0.183
Capability
- Intelligence
- 30.1
- Coding
- not available
- Agentic
- not available
- Omniscience
- -5.1
- Correct
- 44.6%
- Blended price
- $1.74
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 94.3%
Artificial Analysis benchmarks
- GDPval-AA v2
- 38%
- τ³-Banking
- 26%
- SciCode
- 50%
- Humanity’s Last Exam
- 33%
- GPQA Diamond
- 87%
- CritPt
- 17%
- AA-Omniscience
- 47%
- AA-LCR
- 74%
DeepSWE operational cross-check
- Pass@1
- 35.1%
- Avg steps/scored attempt
- 25.15
- Mean cost/scored attempt (USD)
- $0.583
- Mean output tokens/scored attempt
- 11,746.56
- Mean duration/scored attempt (s)
- 230 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
- GPT-6 Luna (Medium)OpenAIQuality Score 46.8Value Score 42.7
- GPT-5.6 Luna (High)OpenAIQuality Score 46.7Value Score 39.9
- GPT-5.2 Codex (Xhigh)OpenAIQuality Score 46.4Value Score 30.1
- GPT-5.2 (Xhigh)OpenAIQuality Score 48.2Value Score 31.3
- GPT-5.4 (Low)OpenAIQuality Score 47.4Value Score 30.2
- GPT-5.5 Instant (June 2026)OpenAIQuality Score 45.9Value Score 27.0