Benchmark
Deep20Bench success rate
Scores are percentages. Higher is better.
- Models measured
- 28
- Scores recorded
- 28
- Sources
- 1
- IQ weight
- 3.27
Score distribution
- 90.7%
- Mean
- 96.7%
- Median
- 12.2%
- Std dev
- 73.3%
- 10th percentile
- 100%
- 90th percentile
- 50%
- Min
This benchmark has a weight of 3.27 for chat models, measured over 28 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5.2qualified-core-v1, anthropic, BX-20261109-official-M0038-001· Deep20Bench | 100% |
| 2 | Gemini 3.8 Flashqualified-core-v1, google-ai-studio, BX-20260908-B-0003-experimental-M0021-001· Deep20Bench | 100% |
| 3 | Gemini 4 Argonqualified-core-v1, google-vertex, BX-20261014-B-0003-official-M0034-002· Deep20Bench | 100% |
| 4 | Gemini 4 Hydrogenqualified-core-v1, google-vertex, BX-20261113-B-0003-official-M0040-001· Deep20Bench | 100% |
| 5 | Gemini 4 Neonqualified-core-v1, google-vertex, BX-20261120-B-0003-official-M0042-001· Deep20Bench | 100% |
| 6 | GPT-6 Astraqualified-core-v1, openai, BX-20260909-B-0003-experimental-M0022-002· Deep20Bench | 100% |
| 7 | GPT-6 Solqualified-core-v1, openai, BX-20260926-B-0003-official-M0029-001· Deep20Bench | 100% |
| 8 | GPT-6.2 Astraqualified-core-v1, openai, BX-20261121-B-0003-official-M0043-001· Deep20Bench | 100% |
| 9 | GPT-6.2 Solqualified-core-v1, openai, BX-20261117-B-0003-official-M0041-001· Deep20Bench | 100% |
| 10 | Grok 4.6qualified-core-v1, xai, BX-20260908-B-0003-experimental-M0015-001· Deep20Bench | 100% |
| 11 | Claude Opus 5.5qualified-core-v1, anthropic, BX-20261103-B-0003-official-M0030-001· Deep20Bench | 96.7% |
| 12 | GPT-5.6 Solqualified-core-v1, openai, BX-20260908-B-0003-experimental-M0010-001· Deep20Bench | 96.7% |
| 13 | GPT-6.1 Solqualified-core-v1, openai, BX-20260929-B-0003-official-M0031-001· Deep20Bench | 96.7% |
| 14 | Muse Spark 1.3 Contributorqualified-core-v1, meta, BX-20260909-B-0003-experimental-M0026-003· Deep20Bench | 96.7% |
| 15 | Muse Wonderqualified-core-v1, meta, BX-20261013-B-0003-OFFICIAL-M0033-002· Deep20Bench | 96.7% |
| 16 | Claude Fable 5.1qualified-core-v1, anthropic, BX-20260908-B-0003-experimental-M0020-001· Deep20Bench | 93.3% |
| 17 | Claude Opus 5qualified-core-v1, anthropic, BX-20260907-B-0003-experimental-M0006-002· Deep20Bench | 93.3% |
| 18 | Gemini 3.7 Flashqualified-core-v1, google-ai-studio, BX-20260908-B-0003-experimental-M0016-001· Deep20Bench | 93.3% |
| 19 | GPT-5.6 Lunaqualified-core-v1, openai, BX-20260908-B-0003-experimental-M0001-001· Deep20Bench | 90% |
| 20 | GPT-6.1 Terraqualified-core-v1, openai, BX-20261027-B-0003-official-M0036-001· Deep20Bench | 90% |
| 21 | Claude Sonnet 5.5qualified-core-v1, anthropic, BX-20261103-B-0003-official-M0032-001· Deep20Bench | 86.7% |
| 22 | Claude Haiku 5.5qualified-core-v1, anthropic, BX-20261023-B-0003-official-M0035-001· Deep20Bench | 83.3% |
| 23 | DeepSeek V4.1 Flash 1017qualified-core-v1, deepinfra, BX-20261028-B-0003-official-M0037-001· Deep20Bench | 83.3% |
| 24 | GPT-6 Lunaqualified-core-v1, openai, BX-20260926-B-0003-official-M0028-001· Deep20Bench | 80% |
| 25 | GLM 5.3 Flashqualified-core-v1, z-ai, BX-20260908-B-0003-experimental-M0023-001· Deep20Bench | 73.3% |
| 26 | Grok 4.7qualified-core-v1, xai, BX-20260926-B-0003-official-M0027-001· Deep20Bench | 73.3% |
| 27 | GPT OSS 120Bqualified-core-v1, cerebras, BX-20260908-B-0003-experimental-M0002-001· Deep20Bench | 66.7% |
| 28 | MiniMax M3qualified-core-v1, coreweave, BX-20260908-B-0003-experimental-M0024-001· Deep20Bench | 50% |
Data credits: Deep20Bench edition 1.1, Patrick Heusser. Results CC BY 4.0; native question scores and fraction-to-percent success rates. (licence)