A task with its own rules.
A Chinese-language academic and professional benchmark spanning humanities, social science, STEM, and applied subjects.
- Organisation
- C-Eval authors
- Version
- 2023
Loading benchmark header
Loading benchmark registry
Knowledge / Benchmark profile
A Chinese-language academic and professional benchmark spanning humanities, social science, STEM, and applied subjects.
Observed results
7 ranked models · higher is better · labels show rank and score
| Model | Rank | Model ID | Provider | Score | Unit |
|---|---|---|---|---|---|
| Qwen3.6 Plus | #1 | qwen3-6-plus | Alibaba Cloud | 93.3 | percent |
| DeepSeek V4 Pro Base | #2 | deepseek-v4-pro-base | DeepSeek | 93.1 | percent |
| Qwen3.5 397B A17B | #3 | qwen3-5-397b | Alibaba Cloud | 93 | percent |
| Claude Opus 4.5 | #4 | claude-opus-4-5 | Anthropic | 92.2 | percent |
| DeepSeek V4 Flash Base | #5 | deepseek-v4-flash-base | DeepSeek | 92.1 | percent |
| Qwen3.6 27B | #6 | qwen3-6-27b | Alibaba Cloud | 91.4 | percent |
| Qwen3.6-35B-A3B | #7 | qwen3-6-35b-a3b | Alibaba Cloud | 90 | percent |
One best compatible score per canonical product · higher is better
| Rank | Model | Weights | Evidence | Score |
|---|---|---|---|---|
| 01 | Qwen3.6 PlusAlibaba Cloud | Closed weights | Source carrier | 93.3% |
| 02 | DeepSeek V4 Pro BaseDeepSeek | Open weights | Source carrier | 93.1% |
| 03 | Qwen3.5 397B A17BAlibaba Cloud | Open weights | Source carrier | 93% |
| 04 | Claude Opus 4.5Anthropic | Closed weights | Source carrier | 92.2% |
| 05 | DeepSeek V4 Flash BaseDeepSeek | Open weights | Source carrier | 92.1% |
| 06 | Qwen3.6 27BAlibaba Cloud | Open weights | Source carrier | 91.4% |
| 07 | Qwen3.6-35B-A3BAlibaba Cloud | Open weights | Source carrier | 90% |
Each distinct published measurement is retained. Same-snapshot canonical and configuration projections appear once.
| Published model / configuration | Score | Evidence & protocol | Source & dates |
|---|---|---|---|
Exact BenchLM registry variant Qwen3.6 Plus; bulk export does not retain a complete upstream harness configuration.Qwen3.6 PlusExact identitySource label without a registered configuration ID Canonical product: qwen3-6-plus | 93.3% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant DeepSeek V4 Pro Base; bulk export does not retain a complete upstream harness configuration.DeepSeek V4 Pro BaseExact identitySource label without a registered configuration ID Canonical product: deepseek-v4-pro-base | 93.1% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Qwen3.5 397B; bulk export does not retain a complete upstream harness configuration.Qwen3.5 397B A17BExact identitySource label without a registered configuration ID Canonical product: qwen3-5-397b | 93% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Claude Opus 4.5; bulk export does not retain a complete upstream harness configuration.Claude Opus 4.5Exact identitySource label without a registered configuration ID Canonical product: claude-opus-4-5 | 92.2% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant DeepSeek V4 Flash Base; bulk export does not retain a complete upstream harness configuration.DeepSeek V4 Flash BaseExact identitySource label without a registered configuration ID Canonical product: deepseek-v4-flash-base | 92.1% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Qwen3.6-27B; bulk export does not retain a complete upstream harness configuration.Qwen3.6 27BExact identitySource label without a registered configuration ID Canonical product: qwen3-6-27b | 91.4% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Qwen3.6-35B-A3B; bulk export does not retain a complete upstream harness configuration.Qwen3.6-35B-A3BExact identitySource label without a registered configuration ID Canonical product: qwen3-6-35b-a3b | 90% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-08-01Observed Checked |
Exact BenchLM registry variant Qwen3.6 Plus; bulk export does not retain a complete upstream harness configuration.Qwen3.6 PlusExact identitySource label without a registered configuration ID Canonical product: qwen3-6-plus | 93.3% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-07-27Observed Checked |
Exact BenchLM registry variant DeepSeek V4 Pro Base; bulk export does not retain a complete upstream harness configuration.DeepSeek V4 Pro BaseExact identitySource label without a registered configuration ID Canonical product: deepseek-v4-pro-base | 93.1% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-07-27Observed Checked |
Exact BenchLM registry variant Qwen3.5 397B; bulk export does not retain a complete upstream harness configuration.Qwen3.5 397B A17BExact identitySource label without a registered configuration ID Canonical product: qwen3-5-397b | 93% | Source carriersource-checkedVersion & system2023 Source-native system | BenchLM public datasets — 2026-07-27Observed Checked |
From result to context
A Chinese-language academic and professional benchmark spanning humanities, social science, STEM, and applied subjects.
The summary shows one best compatible source result per canonical product. Versions, effort settings and execution systems remain attached to the underlying records.
Scores from different versions or harnesses may not be interchangeable. The published source rows preserve those distinctions and their original units. A source result is not automatically an input to a current index.
This catalogue entry preserves available source evidence. Current indices admit only their specifically reviewed tracks and configurations.
Contamination risk: Unknown. Lifecycle: Active.