BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

Mistral AI

Provider prefix
MSTRL
Benchmark Record namespace
013

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-013LG3-001 Mistral Large 3 Artificial Analysis Intelligence Index Overall 15.9 Unknown Primary source MSTRL-LG3
BR-013LG3-002 Mistral Large 3 GPQA Diamond Accuracy 68% Unknown Primary source MSTRL-LG3
BR-013LG3-003 Mistral Large 3 Humanity's Last Exam No tools Overall 4.1% Unknown Primary source MSTRL-LG3
BR-013LG3-004 Mistral Large 3 SciCode Overall 36.2% Unknown Primary source MSTRL-LG3
BR-013LG3-005 Mistral Large 3 tau2-bench Overall 24.6% Unknown Primary source MSTRL-LG3
BR-013LG3-006 Mistral Large 3 tau3-Banking Overall 5.8% Unknown Primary source MSTRL-LG3
BR-013LG3-007 Mistral Large 3 Terminal-Bench Hard Overall 15.9% Unknown Primary source MSTRL-LG3
BR-013LG3-008 Mistral Large 3 Terminal-Bench 2.1 Overall 12% Unknown Primary source MSTRL-LG3
BR-013LG3-009 Mistral Large 3 CritPt Overall 0% Unknown Primary source MSTRL-LG3
BR-013LG3-010 Mistral Large 3 AA-Omniscience Overall -39.4 Unknown Primary source MSTRL-LG3
BR-013LG3-011 Mistral Large 3 AA-Omniscience Accuracy 24.1% Unknown Primary source MSTRL-LG3
BR-013LG3-012 Mistral Large 3 IFBench Overall 36.2% Unknown Primary source MSTRL-LG3
BR-013LG3-013 Mistral Large 3 GDPval-AA Average Normalized Score 6.6% Unknown Primary source MSTRL-LG3
BR-013LG3-014 Mistral Large 3 MMMU-Pro Overall 55.7% Unknown Primary source MSTRL-LG3
BR-013LG3-015 Mistral Large 3 AA-LCR Overall 34.7% Unknown Primary source MSTRL-LG3
BR-013SM3-001 Mistral Small 3 Artificial Analysis Intelligence Index Overall 6.9 Unknown Primary source MSTRL-SM3
BR-013SM3-002 Mistral Small 3 GPQA Diamond Accuracy 46.2% Unknown Primary source MSTRL-SM3
BR-013SM3-003 Mistral Small 3 Humanity's Last Exam No tools Overall 4.1% Unknown Primary source MSTRL-SM3
BR-013SM3-004 Mistral Small 3 SciCode Overall 23.6% Unknown Primary source MSTRL-SM3
BR-013SM3-005 Mistral Small 3 tau2-bench Overall 19.6% Unknown Primary source MSTRL-SM3
BR-013SM3-006 Mistral Small 3 IFBench Overall 26.4% Unknown Primary source MSTRL-SM3
BR-013SM3-007 Mistral Small 3 AA-LCR Overall 0% Unknown Primary source MSTRL-SM3
BR-013SM31-001 Mistral Small 3.1 Artificial Analysis Intelligence Index Overall 14.7 Unknown Primary source MSTRL-SM31
BR-013SM31-002 Mistral Small 3.1 GPQA Diamond Accuracy 45.4% Unknown Primary source MSTRL-SM31
BR-013SM31-003 Mistral Small 3.1 Humanity's Last Exam No tools Overall 4.8% Unknown Primary source MSTRL-SM31
BR-013SM31-004 Mistral Small 3.1 SciCode Overall 26.5% Unknown Primary source MSTRL-SM31
BR-013SM31-005 Mistral Small 3.1 tau2-bench Overall 25.1% Unknown Primary source MSTRL-SM31
BR-013SM31-006 Mistral Small 3.1 tau3-Banking Overall 7% Unknown Primary source MSTRL-SM31
BR-013SM31-007 Mistral Small 3.1 Terminal-Bench Hard Overall 7.6% Unknown Primary source MSTRL-SM31
BR-013SM31-008 Mistral Small 3.1 Terminal-Bench 2.1 Overall 26.2% Unknown Primary source MSTRL-SM31
BR-013SM31-009 Mistral Small 3.1 CritPt Overall 0% Unknown Primary source MSTRL-SM31
BR-013SM31-010 Mistral Small 3.1 AA-Omniscience Overall -50.3 Unknown Primary source MSTRL-SM31
BR-013SM31-011 Mistral Small 3.1 AA-Omniscience Accuracy 15% Unknown Primary source MSTRL-SM31
BR-013SM31-012 Mistral Small 3.1 IFBench Overall 29.9% Unknown Primary source MSTRL-SM31
BR-013SM31-013 Mistral Small 3.1 GDPval-AA Average Normalized Score 4.5% Unknown Primary source MSTRL-SM31
BR-013SM31-014 Mistral Small 3.1 AA-LCR Overall 19.7% Unknown Primary source MSTRL-SM31
BR-013SM32-001 Mistral Small 3.2 Artificial Analysis Intelligence Index Overall 10.6 Unknown Primary source MSTRL-SM32
BR-013SM32-002 Mistral Small 3.2 GPQA Diamond Accuracy 50.5% Unknown Primary source MSTRL-SM32
BR-013SM32-003 Mistral Small 3.2 Humanity's Last Exam No tools Overall 4.3% Unknown Primary source MSTRL-SM32
BR-013SM32-004 Mistral Small 3.2 SciCode Overall 26.4% Unknown Primary source MSTRL-SM32
BR-013SM32-005 Mistral Small 3.2 tau2-bench Overall 29.5% Unknown Primary source MSTRL-SM32
BR-013SM32-006 Mistral Small 3.2 tau3-Banking Overall 6% Unknown Primary source MSTRL-SM32
BR-013SM32-007 Mistral Small 3.2 Terminal-Bench Hard Overall 6.8% Unknown Primary source MSTRL-SM32
BR-013SM32-008 Mistral Small 3.2 Terminal-Bench 2.1 Overall 5.6% Unknown Primary source MSTRL-SM32
BR-013SM32-009 Mistral Small 3.2 CritPt Overall 0% Unknown Primary source MSTRL-SM32
BR-013SM32-010 Mistral Small 3.2 AA-Omniscience Overall -50.4 Unknown Primary source MSTRL-SM32
BR-013SM32-011 Mistral Small 3.2 AA-Omniscience Accuracy 14.7% Unknown Primary source MSTRL-SM32
BR-013SM32-012 Mistral Small 3.2 IFBench Overall 33.5% Unknown Primary source MSTRL-SM32
BR-013SM32-013 Mistral Small 3.2 GDPval-AA Average Normalized Score 0% Unknown Primary source MSTRL-SM32
BR-013SM32-014 Mistral Small 3.2 MMMU-Pro Overall 48% Unknown Primary source MSTRL-SM32
BR-013SM32-015 Mistral Small 3.2 AA-LCR Overall 17.3% Unknown Primary source MSTRL-SM32
BR-013SM4-001 Mistral Small 4 GPQA Diamond Accuracy 71.2 Unknown Primary source MSTRL-SM4
BR-013SM4-002 Mistral Small 4 Artificial Analysis Intelligence Index Overall 12.4 Unknown Primary source MSTRL-SM4
BR-013SM4-003 Mistral Small 4 Humanity's Last Exam No tools Overall 3.7% Unknown Primary source MSTRL-SM4
BR-013SM4-004 Mistral Small 4 SciCode Overall 28.1% Unknown Primary source MSTRL-SM4
BR-013SM4-005 Mistral Small 4 tau2-bench Overall 18.4% Unknown Primary source MSTRL-SM4
BR-013SM4-006 Mistral Small 4 Terminal-Bench Hard Overall 10.6% Unknown Primary source MSTRL-SM4
BR-013SM4-007 Mistral Small 4 CritPt Overall 0.3% Unknown Primary source MSTRL-SM4
BR-013SM4-008 Mistral Small 4 AA-Omniscience Overall -48.4 Unknown Primary source MSTRL-SM4
BR-013SM4-009 Mistral Small 4 AA-Omniscience Accuracy 16.3% Unknown Primary source MSTRL-SM4
BR-013SM4-010 Mistral Small 4 IFBench Overall 32.8% Unknown Primary source MSTRL-SM4
BR-013SM4-011 Mistral Small 4 MMMU-Pro Overall 46.5% Unknown Primary source MSTRL-SM4
BR-013SM4-012 Mistral Small 4 AA-LCR Overall 21.3% Unknown Primary source MSTRL-SM4
BR-013SM4-013 Mistral Small 4 Artificial Analysis Intelligence Index Overall 19.6 Unknown Primary source MSTRL-SM4
BR-013SM4-014 Mistral Small 4 Humanity's Last Exam No tools Overall 9.5% Unknown Primary source MSTRL-SM4
BR-013SM4-015 Mistral Small 4 SciCode Overall 38% Unknown Primary source MSTRL-SM4
BR-013SM4-016 Mistral Small 4 tau2-bench Overall 41.2% Unknown Primary source MSTRL-SM4
BR-013SM4-017 Mistral Small 4 tau3-Banking Overall 5.2% Unknown Primary source MSTRL-SM4
BR-013SM4-018 Mistral Small 4 Terminal-Bench Hard Overall 17.4% Unknown Primary source MSTRL-SM4
BR-013SM4-019 Mistral Small 4 Terminal-Bench 2.1 Overall 21% Unknown Primary source MSTRL-SM4
BR-013SM4-020 Mistral Small 4 CritPt Overall 0.3% Unknown Primary source MSTRL-SM4
BR-013SM4-021 Mistral Small 4 AA-Omniscience Overall -29.9 Unknown Primary source MSTRL-SM4
BR-013SM4-022 Mistral Small 4 AA-Omniscience Accuracy 22.1% Unknown Primary source MSTRL-SM4
BR-013SM4-023 Mistral Small 4 IFBench Overall 48.2% Unknown Primary source MSTRL-SM4
BR-013SM4-024 Mistral Small 4 GDPval-AA Average Normalized Score 4.4% Unknown Primary source MSTRL-SM4
BR-013SM4-025 Mistral Small 4 MMMU-Pro Overall 56.8% Unknown Primary source MSTRL-SM4
BR-013SM4-026 Mistral Small 4 AA-LCR Overall 44.7% Unknown Primary source MSTRL-SM4