Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

Terminal-Bench Hard

Benchmark Family
Terminal-Bench Hard
Organization
Laude Institute
Status
ACTIVE

Versions / Variants

Version or VariantReferenceStatusRecords
Unspecifiedterminal-bench-hard/defaultACTIVE345

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-007QWEN3635BA3B-006 Qwen3.6 35B A3B Terminal-Bench Hard Overall 25.8% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN3635BA3B-020 Qwen3.6 35B A3B Terminal-Bench Hard Overall 34.8% Unknown Primary source QWEN-QWEN3635BA3B
BR-007QWEN36MAXPREVIEW-006 Qwen3.6 Max Preview Terminal-Bench Hard Overall 43.9% Unknown Primary source QWEN-QWEN36MAXPREVIEW
BR-007QWEN36PLUS-007 Qwen3.6 Plus Terminal-Bench Hard Overall 43.9% Unknown Primary source QWEN-QWEN36PLUS
BR-007QWEN37MAX-007 Qwen3.7 Max Terminal-Bench Hard Overall 50.8% Unknown Primary source QWEN-QWEN37MAX
BR-007QWEN37PLUS-007 Qwen3.7 Plus Terminal-Bench Hard Overall 47% Unknown Primary source QWEN-QWEN37PLUS
BR-007QWEN38B-007 Qwen3 8B Terminal-Bench Hard Overall 2.3% Unknown Primary source QWEN-QWEN38B
BR-007QWEN38B-020 Qwen3 8B Terminal-Bench Hard Overall 2.3% Unknown Primary source QWEN-QWEN38B
BR-007QWEN3CODER30BA3BINSTRUCT-006 Qwen3 Coder 30B A3B Instruct Terminal-Bench Hard Overall 15.2% Unknown Primary source QWEN-QWEN3CODER30BA3BINSTRUCT
BR-007QWEN3CODER480BA35BINSTRUCT-006 Qwen3 Coder 480B A35B Instruct Terminal-Bench Hard Overall 18.9% Unknown Primary source QWEN-QWEN3CODER480BA35BINSTRUCT
BR-007QWEN3CODERNEXT-007 Qwen3 Coder Next Terminal-Bench Hard Overall 18.2% Unknown Primary source QWEN-QWEN3CODERNEXT
BR-007QWEN3MAX-006 Qwen3 Max Terminal-Bench Hard Overall 20.5% Unknown Primary source QWEN-QWEN3MAX
BR-007QWEN3MAXPREVIEW-006 Qwen3 Max (Preview) Terminal-Bench Hard Overall 19.7% Unknown Primary source QWEN-QWEN3MAXPREVIEW
BR-007QWEN3MAXTHINKING-006 Qwen3 Max Thinking Terminal-Bench Hard Overall 24.2% Unknown Primary source QWEN-QWEN3MAXTHINKING
BR-007QWEN3MAXTHINKINGPREVIEW-006 Qwen3 Max Thinking (Preview) Terminal-Bench Hard Overall 17.4% Unknown Primary source QWEN-QWEN3MAXTHINKINGPREVIEW
BR-007QWEN3NEXT80BA3B-007 Qwen3 Next 80B A3B Terminal-Bench Hard Overall 9.8% Unknown Primary source QWEN-QWEN3NEXT80BA3B
BR-007QWEN3NEXT80BA3BINSTRUCT-006 Qwen3 Next 80B A3B Instruct Terminal-Bench Hard Overall 7.6% Unknown Primary source QWEN-QWEN3NEXT80BA3BINSTRUCT
BR-007QWEN3OMNI30BA3B-006 Qwen3 Omni 30B A3B Terminal-Bench Hard Overall 3.8% Unknown Primary source QWEN-QWEN3OMNI30BA3B
BR-007QWEN3OMNI30BA3BINSTRUCT-006 Qwen3 Omni 30B A3B Instruct Terminal-Bench Hard Overall 1.5% Unknown Primary source QWEN-QWEN3OMNI30BA3BINSTRUCT
BR-007QWEN3VL235BA22B-006 Qwen3 VL 235B A22B Terminal-Bench Hard Overall 11.4% Unknown Primary source QWEN-QWEN3VL235BA22B
BR-007QWEN3VL235BA22BINSTRUCT-006 Qwen3 VL 235B A22B Instruct Terminal-Bench Hard Overall 6.8% Unknown Primary source QWEN-QWEN3VL235BA22BINSTRUCT
BR-007QWEN3VL30BA3B-006 Qwen3 VL 30B A3B Terminal-Bench Hard Overall 5.3% Unknown Primary source QWEN-QWEN3VL30BA3B
BR-007QWEN3VL30BA3BINSTRUCT-006 Qwen3 VL 30B A3B Instruct Terminal-Bench Hard Overall 6.1% Unknown Primary source QWEN-QWEN3VL30BA3BINSTRUCT
BR-007QWEN3VL32B-006 Qwen3 VL 32B Terminal-Bench Hard Overall 7.6% Unknown Primary source QWEN-QWEN3VL32B
BR-007QWEN3VL32BINSTRUCT-006 Qwen3 VL 32B Instruct Terminal-Bench Hard Overall 8.3% Unknown Primary source QWEN-QWEN3VL32BINSTRUCT
BR-007QWEN3VL4B-006 Qwen3 VL 4B Terminal-Bench Hard Overall 1.5% Unknown Primary source QWEN-QWEN3VL4B
BR-007QWEN3VL4BINSTRUCT-006 Qwen3 VL 4B Instruct Terminal-Bench Hard Overall 0% Unknown Primary source QWEN-QWEN3VL4BINSTRUCT
BR-007QWEN3VL8B-006 Qwen3 VL 8B Terminal-Bench Hard Overall 3.8% Unknown Primary source QWEN-QWEN3VL8B
BR-007QWEN3VL8BINSTRUCT-006 Qwen3 VL 8B Instruct Terminal-Bench Hard Overall 2.3% Unknown Primary source QWEN-QWEN3VL8BINSTRUCT
BR-008DEEPSEEKR10528MAY25-006 DeepSeek R1 0528 (May '25) Terminal-Bench Hard Overall 15.9% Unknown Primary source DPSK-DEEPSEEKR10528MAY25
BR-008DEEPSEEKR10528QWEN38B-006 DeepSeek R1 0528 Qwen3 8B Terminal-Bench Hard Overall 1.5% Unknown Primary source DPSK-DEEPSEEKR10528QWEN38B
BR-008DEEPSEEKR1DISTILLLLAMA70B-006 DeepSeek R1 Distill Llama 70B Terminal-Bench Hard Overall 1.5% Unknown Primary source DPSK-DEEPSEEKR1DISTILLLLAMA70B
BR-008DEEPSEEKR1JAN25-007 DeepSeek R1 (Jan '25) Terminal-Bench Hard Overall 6.1% Unknown Primary source DPSK-DEEPSEEKR1JAN25
BR-008DEEPSEEKV30324-007 DeepSeek V3 0324 Terminal-Bench Hard Overall 15.2% Unknown Primary source DPSK-DEEPSEEKV30324
BR-008DEEPSEEKV31-006 DeepSeek V3.1 Terminal-Bench Hard Overall 25% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31-017 DeepSeek V3.1 Terminal-Bench Hard Overall 24.2% Unknown Primary source DPSK-DEEPSEEKV31
BR-008DEEPSEEKV31TERMINUS-007 DeepSeek V3.1 Terminus Terminal-Bench Hard Overall 30.3% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV31TERMINUS-020 DeepSeek V3.1 Terminus Terminal-Bench Hard Overall 31.8% Unknown Primary source DPSK-DEEPSEEKV31TERMINUS
BR-008DEEPSEEKV32-006 DeepSeek V3.2 Terminal-Bench Hard Overall 32.6% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32-018 DeepSeek V3.2 Terminal-Bench Hard Overall 35.6% Unknown Primary source DPSK-DEEPSEEKV32
BR-008DEEPSEEKV32EXP-006 DeepSeek V3.2 Exp Terminal-Bench Hard Overall 25% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32EXP-017 DeepSeek V3.2 Exp Terminal-Bench Hard Overall 31.1% Unknown Primary source DPSK-DEEPSEEKV32EXP
BR-008DEEPSEEKV32SPECIALE-006 DeepSeek V3.2 Speciale Terminal-Bench Hard Overall 34.8% Unknown Primary source DPSK-DEEPSEEKV32SPECIALE
BR-008DEEPSEEKV3DEC24-007 DeepSeek V3 (Dec '24) Terminal-Bench Hard Overall 6.8% Unknown Primary source DPSK-DEEPSEEKV3DEC24
BR-008DEEPSEEKV4FLASH-006 DeepSeek V4 Flash Terminal-Bench Hard Overall 38.6% Unknown Primary source DPSK-DEEPSEEKV4FLASH
BR-008DEEPSEEKV4FLASH-017 DeepSeek V4 Flash Terminal-Bench Hard Overall 34.1% Unknown Primary source DPSK-DEEPSEEKV4FLASH
BR-008DEEPSEEKV4FLASH-029 DeepSeek V4 Flash Terminal-Bench Hard Overall 35.6% Unknown Primary source DPSK-DEEPSEEKV4FLASH
BR-008DEEPSEEKV4PRO-006 DeepSeek V4 Pro Terminal-Bench Hard Overall 41.7% Unknown Primary source DPSK-DEEPSEEKV4PRO
BR-008DEEPSEEKV4PRO-018 DeepSeek V4 Pro Terminal-Bench Hard Overall 36.4% Unknown Primary source DPSK-DEEPSEEKV4PRO
BR-008DEEPSEEKV4PRO-030 DeepSeek V4 Pro Terminal-Bench Hard Overall 46.2% Unknown Primary source DPSK-DEEPSEEKV4PRO
BR-009LLAMA31INSTRUCT405B-006 Llama 3.1 Instruct 405B Terminal-Bench Hard Overall 6.8% Unknown Primary source META-LLAMA31INSTRUCT405B
BR-009LLAMA31INSTRUCT70B-006 Llama 3.1 Instruct 70B Terminal-Bench Hard Overall 3% Unknown Primary source META-LLAMA31INSTRUCT70B
BR-009LLAMA31INSTRUCT8B-007 Llama 3.1 Instruct 8B Terminal-Bench Hard Overall 0.8% Unknown Primary source META-LLAMA31INSTRUCT8B
BR-009LLAMA32INSTRUCT11BVISION-006 Llama 3.2 Instruct 11B (Vision) Terminal-Bench Hard Overall 0.8% Unknown Primary source META-LLAMA32INSTRUCT11BVISION
BR-009LLAMA32INSTRUCT1B-006 Llama 3.2 Instruct 1B Terminal-Bench Hard Overall 0% Unknown Primary source META-LLAMA32INSTRUCT1B
BR-009LLAMA33INSTRUCT70B-007 Llama 3.3 Instruct 70B Terminal-Bench Hard Overall 3% Unknown Primary source META-LLAMA33INSTRUCT70B
BR-009LLAMA3INSTRUCT70B-006 Llama 3 Instruct 70B Terminal-Bench Hard Overall 0.8% Unknown Primary source META-LLAMA3INSTRUCT70B
BR-009LLAMA3INSTRUCT8B-006 Llama 3 Instruct 8B Terminal-Bench Hard Overall 0% Unknown Primary source META-LLAMA3INSTRUCT8B
BR-009LLAMA4MAVERICK-007 Llama 4 Maverick Terminal-Bench Hard Overall 6.8% Unknown Primary source META-LLAMA4MAVERICK
BR-009LLAMA4SCOUT-007 Llama 4 Scout Terminal-Bench Hard Overall 1.5% Unknown Primary source META-LLAMA4SCOUT
BR-009MUSESPARK-007 Muse Spark Terminal-Bench Hard Overall 45.5% Unknown Primary source META-MUSESPARK
BR-010KIMIK2-006 Kimi K2 Terminal-Bench Hard Overall 15.9% Unknown Primary source KIMI-KIMIK2
BR-010KIMIK20905-006 Kimi K2 0905 Terminal-Bench Hard Overall 23.5% Unknown Primary source KIMI-KIMIK20905
BR-010KIMIK25-006 Kimi K2.5 Terminal-Bench Hard Overall 34.8% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK25-019 Kimi K2.5 Terminal-Bench Hard Overall 18.9% Unknown Primary source KIMI-KIMIK25
BR-010KIMIK26-007 Kimi K2.6 Terminal-Bench Hard Overall 43.9% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK26-023 Kimi K2.6 Terminal-Bench Hard Overall 37.9% Unknown Primary source KIMI-KIMIK26
BR-010KIMIK27CODE-007 Kimi K2.7 Code Terminal-Bench Hard Overall 44.7% Unknown Primary source KIMI-KIMIK27CODE
BR-010KIMIK2THINKING-006 Kimi K2 Thinking Terminal-Bench Hard Overall 31.1% Unknown Primary source KIMI-KIMIK2THINKING
BR-010KIMILINEAR48BA3BINSTRUCT-006 Kimi Linear 48B A3B Instruct Terminal-Bench Hard Overall 11.4% Unknown Primary source KIMI-KIMILINEAR48BA3BINSTRUCT
BR-01145-006 GLM-4.5 Terminal-Bench Hard Overall 22% Unknown Primary source GLM-45
BR-01146-007 GLM-4.6 Terminal-Bench Hard Overall 25% Unknown Primary source GLM-46
BR-01146-020 GLM-4.6 Terminal-Bench Hard Overall 28.8% Unknown Primary source GLM-46
BR-01147-007 GLM-4.7 Terminal-Bench Hard Overall 31.8% Unknown Primary source GLM-47
BR-01147-020 GLM-4.7 Terminal-Bench Hard Overall 30.3% Unknown Primary source GLM-47
BR-0115-006 GLM-5 Terminal-Bench Hard Overall 43.2% Unknown Primary source GLM-5
BR-0115-018 GLM-5 Terminal-Bench Hard Overall 39.4% Unknown Primary source GLM-5
BR-01151-007 GLM-5.1 Terminal-Bench Hard Overall 43.2% Unknown Primary source GLM-51
BR-01151-021 GLM-5.1 Terminal-Bench Hard Overall 35.6% Unknown Primary source GLM-51
BR-01152-032 GLM-5.2 Terminal-Bench Hard Overall 50.8% Unknown Primary source GLM-52
BR-011GLM45AIR-006 GLM-4.5-Air Terminal-Bench Hard Overall 20.5% Unknown Primary source GLM-GLM45AIR
BR-011GLM45V-006 GLM-4.5V Terminal-Bench Hard Overall 6.8% Unknown Primary source GLM-GLM45V
BR-011GLM45V-018 GLM-4.5V Terminal-Bench Hard Overall 5.3% Unknown Primary source GLM-GLM45V
BR-011GLM46V-006 GLM-4.6V Terminal-Bench Hard Overall 3% Unknown Primary source GLM-GLM46V
BR-011GLM46V-018 GLM-4.6V Terminal-Bench Hard Overall 14.4% Unknown Primary source GLM-GLM46V
BR-011GLM47FLASH-006 GLM-4.7-Flash Terminal-Bench Hard Overall 22% Unknown Primary source GLM-GLM47FLASH
BR-011GLM47FLASH-017 GLM-4.7-Flash Terminal-Bench Hard Overall 3.8% Unknown Primary source GLM-GLM47FLASH
BR-011GLM5TURBO-006 GLM-5-Turbo Terminal-Bench Hard Overall 33.3% Unknown Primary source GLM-GLM5TURBO
BR-011GLM5VTURBO-006 GLM 5V Turbo Terminal-Bench Hard Overall 32.6% Unknown Primary source GLM-GLM5VTURBO
BR-012MINIMAXM140K-006 MiniMax M1 40k Terminal-Bench Hard Overall 2.3% Unknown Primary source MMAX-MINIMAXM140K
BR-012MINIMAXM180K-006 MiniMax M1 80k Terminal-Bench Hard Overall 3% Unknown Primary source MMAX-MINIMAXM180K
BR-012MINIMAXM2-006 MiniMax-M2 Terminal-Bench Hard Overall 25.8% Unknown Primary source MMAX-MINIMAXM2
BR-012MINIMAXM21-006 MiniMax-M2.1 Terminal-Bench Hard Overall 28.8% Unknown Primary source MMAX-MINIMAXM21
BR-012MINIMAXM25-006 MiniMax-M2.5 Terminal-Bench Hard Overall 34.8% Unknown Primary source MMAX-MINIMAXM25
BR-012MINIMAXM27-007 MiniMax-M2.7 Terminal-Bench Hard Overall 39.4% Unknown Primary source MMAX-MINIMAXM27
BR-012MINIMAXM3-007 MiniMax-M3 Terminal-Bench Hard Overall 42.4% Unknown Primary source MMAX-M3
BR-013LG3-007 Mistral Large 3 Terminal-Bench Hard Overall 15.9% Unknown Primary source MSTRL-LG3
BR-013SM31-007 Mistral Small 3.1 Terminal-Bench Hard Overall 7.6% Unknown Primary source MSTRL-SM31
BR-013SM32-007 Mistral Small 3.2 Terminal-Bench Hard Overall 6.8% Unknown Primary source MSTRL-SM32
BR-013SM4-006 Mistral Small 4 Terminal-Bench Hard Overall 10.6% Unknown Primary source MSTRL-SM4