# Terminal-Bench 4.1 → Terminal-Bench Hard

Calibration · https://benchgap.net/calibration/terminal-bench41/current/to/terminal-bench-hard/current · data retrieved 2026-11-18

Terminal-Bench Hard is estimated from Terminal-Bench 4.1 with a linear curve fitted on 5 models measured on both: y = 0.2775·x + 0.5245, R² = 0.90, cross-validated error 2.8 pp. It is used for 41 estimates.

| Estimated model | Terminal-Bench 4.1 | Terminal-Bench Hard | Source |
|---|---|---|---|
| [Claude Fable 5.2](https://benchgap.net/model/claude-fable-5-2.md) | 65.8% | 70.7% | estimated ± 2.8 pp, low confidence |
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 65.8% | 70.7% | estimated ± 2.8 pp, low confidence |
| [Gemini 4 Carbon](https://benchgap.net/model/gemini-4-carbon.md) | 64.6% | 70.4% | estimated ± 2.8 pp, low confidence |
| [Claude Sonnet 5.5](https://benchgap.net/model/claude-sonnet-5-5.md) | 63.9% | 70.2% | estimated ± 2.8 pp, low confidence |
| [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol.md) | 60.9% | 69.4% | estimated ± 2.8 pp, low confidence |
| [GPT-6 Astra](https://benchgap.net/model/gpt-6-astra.md) | 60.3% | 69.2% | estimated ± 2.8 pp, low confidence |
| [Kimi K3.1 Pro](https://benchgap.net/model/kimi-3-1-pro.md) | 59.7% | 69.0% | estimated ± 2.8 pp, low confidence |
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 57.6% | 68.4% | estimated ± 2.8 pp, low confidence |
| [Gemini 4 Hydrogen](https://benchgap.net/model/gemini-4-hydrogen.md) | 56.4% | 68.1% | estimated ± 2.8 pp, low confidence |
| [Gemini 4 Argon](https://benchgap.net/model/gemini-4-argon.md) | 55.5% | 67.9% | estimated ± 2.8 pp, low confidence |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 53.3% | 67.2% | estimated ± 2.8 pp, low confidence |
| [GPT-6.1 Terra](https://benchgap.net/model/gpt-6-1-terra.md) | 53.3% | 67.2% | estimated ± 2.8 pp, low confidence |
| [GPT-6 Sol](https://benchgap.net/model/gpt-6-sol.md) | 50.3% | 66.4% | estimated ± 2.8 pp, low confidence |
| [Muse Wonder](https://benchgap.net/model/muse-wonder.md) | 47.0% | 65.5% | estimated ± 2.8 pp, low confidence |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 41.2% | 63.9% | estimated ± 2.8 pp, medium confidence |
| [Claude Haiku 5.5](https://benchgap.net/model/claude-haiku-5-5.md) | 40.0% | 63.6% | estimated ± 2.8 pp, medium confidence |
| [Grok 4.7](https://benchgap.net/model/grok-4-7.md) | 38.8% | 63.2% | estimated ± 2.8 pp, medium confidence |
| [DeepSeek V4.1 Flash 1017](https://benchgap.net/model/deepseek-v4-1-flash.md) | 38.5% | 63.1% | estimated ± 2.8 pp, medium confidence |
| [Hy4](https://benchgap.net/model/hy4.md) | 37.9% | 63.0% | estimated ± 2.8 pp, medium confidence |
| [GLM-5.3-Flash](https://benchgap.net/model/glm-5-3-flash.md) | 37.0% | 62.7% | estimated ± 2.8 pp, medium confidence |
| [Muse Ember](https://benchgap.net/model/muse-ember.md) | 30.6% | 60.9% | estimated ± 2.8 pp, medium confidence |
| [Mistral Large 4](https://benchgap.net/model/mistral-large-4.md) | 27.6% | 60.1% | estimated ± 2.8 pp, medium confidence |
| [MiMo-V2.6-Pro](https://benchgap.net/model/mimo-v2-6-pro.md) | 27.0% | 59.9% | estimated ± 2.8 pp, medium confidence |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 23.0% | 58.8% | estimated ± 2.8 pp, medium confidence |
| [Ember-1](https://benchgap.net/model/ember-1.md) | 21.8% | 58.5% | estimated ± 2.8 pp, medium confidence |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 21.5% | 58.4% | estimated ± 2.8 pp, medium confidence |
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 19.7% | 57.9% | estimated ± 2.8 pp, medium confidence |
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 18.2% | 57.5% | estimated ± 2.8 pp, medium confidence |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 17.6% | 57.3% | estimated ± 2.8 pp, medium confidence |
| [MiMo-V2.6-Flash](https://benchgap.net/model/mimo-v2-6-flash.md) | 16.1% | 56.9% | estimated ± 2.8 pp, medium confidence |
| [GPT-6 Luna](https://benchgap.net/model/gpt-6-luna.md) | 15.2% | 56.7% | estimated ± 2.8 pp, medium confidence |
| [Muse Spark 1.3](https://benchgap.net/model/muse-spark-1-3.md) | 14.9% | 56.6% | estimated ± 2.8 pp, medium confidence |
| [Gemini 3.7 Flash](https://benchgap.net/model/gemini-3-7-flash.md) | 12.4% | 55.9% | estimated ± 2.8 pp, medium confidence |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 12.4% | 55.9% | estimated ± 2.8 pp, medium confidence |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 12.1% | 55.8% | estimated ± 2.8 pp, medium confidence |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 7.6% | 54.6% | estimated ± 2.8 pp, medium confidence |
| [DeepSeek V4 Pro](https://benchgap.net/model/deepseek-v4-pro.md) | 6.7% | 54.3% | estimated ± 2.8 pp, medium confidence |
| [Beam 1.0 501B-A23B](https://benchgap.net/model/reflection-beam.md) | 6.4% | 54.2% | estimated ± 2.8 pp, medium confidence |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 0.9% | 52.7% | estimated ± 2.8 pp, low confidence |
| [Nemotron 3.5 Super VL 120B A12B](https://benchgap.net/model/nemotron-3-5-super-vl-120b-a12b.md) | 0.3% | 52.5% | estimated ± 2.8 pp, low confidence |
| [Inkling](https://benchgap.net/model/inkling.md) | 0.0% | 52.5% | estimated ± 2.8 pp, low confidence |

## Fitted on

| Model | Terminal-Bench 4.1 | Terminal-Bench Hard |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 44.9% | 62.9% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 23.6% | 58.3% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 2.7% | 53.8% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 1.8% | 52.3% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 38.5% | 65.9% |
