{ "results": { "humaneval_instruct": { "name": "humaneval_instruct", "alias": "humaneval_instruct", "sample_len": 164, "pass@1,create_test": 0.0, "pass@1_stderr,create_test": 0.0 }, "mbpp_plus_instruct": { "name": "mbpp_plus_instruct", "alias": "mbpp_plus_instruct", "sample_len": 378, "pass_at_1,extract_code": 0.0, "pass_at_1_stderr,extract_code": 0.0 }, "gsm8k_cot": { "name": "gsm8k_cot", "alias": "gsm8k_cot", "sample_len": 1319, "exact_match,strict-match": 0.6724791508718726, "exact_match_stderr,strict-match": 0.01292710221042672, "exact_match,flexible-extract": 0.9431387414708112, "exact_match_stderr,flexible-extract": 0.006378790242099631 }, "minerva_math500": { "name": "minerva_math500", "alias": "minerva_math500", "sample_len": 500, "exact_match,none": 0.006, "exact_match_stderr,none": 0.003457152557758369, "math_verify,none": 0.6, "math_verify_stderr,none": 0.02193084412072858 }, "arc_challenge_chat": { "name": "arc_challenge_chat", "alias": "arc_challenge_chat", "sample_len": 1172, "exact_match,remove_whitespace": 0.0, "exact_match_stderr,remove_whitespace": 0.0 }, "ifeval": { "name": "ifeval", "alias": "ifeval", "sample_len": 541, "prompt_level_strict_acc,none": 0.5138632162661737, "prompt_level_strict_acc_stderr,none": 0.0215083020678561, "inst_level_strict_acc,none": 0.4856115107913669, "inst_level_strict_acc_stderr,none": "N/A", "prompt_level_loose_acc,none": 0.5175600739371534, "prompt_level_loose_acc_stderr,none": 0.02150330051338897, "inst_level_loose_acc,none": 0.4880095923261391, "inst_level_loose_acc_stderr,none": "N/A" } }, "group_subtasks": {}, "configs": { "arc_challenge_chat": { "task": "arc_challenge_chat", "dataset_path": "allenai/ai2_arc", "dataset_name": "ARC-Challenge", "training_split": "train", "validation_split": "validation", "test_split": "test", "fewshot_split": "train", "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\\nQuestion: {{question.strip()}}\\nA. {{choices.text[0]}}\\nB. {{choices.text[1]}}\\nC. {{choices.text[2]}}{% if choices.text|length > 3 %}\\nD. {{choices.text[3]}}{% endif %}\\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_target": "{{ 'ABCD'[answerKey|int - 1] if answerKey|string in '1234' else answerKey }}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "default", "split": "train", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Given the following question and four candidate answers (A, B, C and D), choose the best answer.\\nQuestion: {{question.strip()}}\\nA. {{choices.text[0]}}\\nB. {{choices.text[1]}}\\nC. {{choices.text[2]}}{% if choices.text|length > 3 %}\\nD. {{choices.text[3]}}{% endif %}\\nYour response should end with \"The best answer is [the_answer_letter]\" where the [the_answer_letter] is one of A, B, C or D.", "doc_to_choice": null, "doc_to_target": "{{ 'ABCD'[answerKey|int - 1] if answerKey|string in '1234' else answerKey }}", "gen_prefix": "The best answer is", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 0, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": true } ], "output_type": "generate_until", "generation_kwargs": { "max_gen_toks": 100, "until": [ "\n\n", "." ] }, "repeats": 1, "filter_list": [ { "name": "remove_whitespace", "filter": [ { "function": "remove_whitespace" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "gen_prefix": "The best answer is", "metadata": { "version": 1.0, "base_url": "http://192.168.20.241:8888/v1/chat/completions", "model": "DeepSeek-v4.1-Flash-EXL3", "max_gen_toks": 1024, "temperature": 0, "num_ctx": 16384, "config_source": "/opt/bench/venv/lib/python3.13/site-packages/lm_eval/tasks/arc/arc_challenge_chat.yaml" } }, "gsm8k_cot": { "task": "gsm8k_cot", "dataset_path": "openai/gsm8k", "dataset_name": "main", "test_split": "test", "doc_to_text": "Q: {{question}}\nA:", "doc_to_target": "{{answer.split('####')[-1].strip() if answer is defined else target}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": null, "process_docs": null, "fewshot_indices": null, "samples": [ { "question": "There are 15 trees in the grove. Grove workers will plant trees in the grove today. After they are done, there will be 21 trees. How many trees did the grove workers plant today?", "target": "There are 15 trees originally. Then there were 21 trees after some more were planted. So there must have been 21 - 15 = 6. The answer is 6." }, { "question": "If there are 3 cars in the parking lot and 2 more cars arrive, how many cars are in the parking lot?", "target": "There are originally 3 cars. 2 more cars arrive. 3 + 2 = 5. The answer is 5." }, { "question": "Leah had 32 chocolates and her sister had 42. If they ate 35, how many pieces do they have left in total?", "target": "Originally, Leah had 32 chocolates. Her sister had 42. So in total they had 32 + 42 = 74. After eating 35, they had 74 - 35 = 39. The answer is 39." }, { "question": "Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops did Jason give to Denny?", "target": "Jason started with 20 lollipops. Then he had 12 after giving some to Denny. So he gave Denny 20 - 12 = 8. The answer is 8." }, { "question": "Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?", "target": "Shawn started with 5 toys. If he got 2 toys each from his mom and dad, then that is 4 more toys. 5 + 4 = 9. The answer is 9." }, { "question": "There were nine computers in the server room. Five more computers were installed each day, from monday to thursday. How many computers are now in the server room?", "target": "There were originally 9 computers. For each of 4 days, 5 more computers were added. So 5 * 4 = 20 computers were added. 9 + 20 is 29. The answer is 29." }, { "question": "Michael had 58 golf balls. On tuesday, he lost 23 golf balls. On wednesday, he lost 2 more. How many golf balls did he have at the end of wednesday?", "target": "Michael started with 58 golf balls. After losing 23 on tuesday, he had 58 - 23 = 35. After losing 2 more, he had 35 - 2 = 33 golf balls. The answer is 33." }, { "question": "Olivia has $23. She bought five bagels for $3 each. How much money does she have left?", "target": "Olivia had 23 dollars. 5 bagels for 3 dollars each will be 5 x 3 = 15 dollars. So she has 23 - 15 dollars left. 23 - 15 is 8. The answer is 8." } ], "doc_to_text": "Q: {{question}}\nA:", "doc_to_choice": null, "doc_to_target": "{{answer.split('####')[-1].strip() if answer is defined else target}}", "gen_prefix": null, "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 8, "metric_list": [ { "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": false, "metric": "exact_match", "regexes_to_ignore": [ ",", "\\$", "(?s).*#### ", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "do_sample": false, "until": [ "Q:", "", "<|im_end|>" ] }, "repeats": 1, "filter_list": [ { "filter": [ { "function": "regex", "regex_pattern": "The answer is (\\-?[0-9\\.\\,]+)." }, { "function": "take_first" } ], "name": "strict-match" }, { "filter": [ { "function": "regex", "group_select": -1, "regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)" }, { "function": "take_first" } ], "name": "flexible-extract" } ], "should_decontaminate": false, "metadata": { "version": 3.0, "base_url": "http://192.168.20.241:8888/v1/chat/completions", "model": "DeepSeek-v4.1-Flash-EXL3", "max_gen_toks": 1024, "temperature": 0, "num_ctx": 16384, "config_source": "/opt/bench/venv/lib/python3.13/site-packages/lm_eval/tasks/gsm8k/gsm8k-cot.yaml" } }, "humaneval_instruct": { "task": "humaneval_instruct", "dataset_path": "openai/openai_humaneval", "test_split": "test", "doc_to_text": "Write a solution to the following problem and make sure that it passes the tests:\n```python\n{{ prompt }}\n```\n", "doc_to_target": "{{test}}\ncheck({{entry_point}})", "unsafe_code": true, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "default", "split": null, "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Write a solution to the following problem and make sure that it passes the tests:\n```python\n{{ prompt }}\n```\n", "doc_to_choice": null, "doc_to_target": "{{test}}\ncheck({{entry_point}})", "gen_prefix": "Here is the completed function:\n```python\n{{ prompt }}\n", "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 0, "metric_list": [ { "metric": "def pass_at_k(references: list[str], predictions: list[list[str]], k: list[int] = None):\n global compute_\n assert k is not None\n if isinstance(k, int):\n k = [k]\n res = compute_.compute(\n references=references,\n predictions=predictions,\n k=k,\n )\n return res[0]\n", "aggregation": "mean", "higher_is_better": true, "k": [ 1 ] } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "\nclass", "\ndef", "\n#", "\nif", "\nprint" ], "max_gen_toks": 1024, "do_sample": false }, "repeats": 1, "filter_list": [ { "name": "create_test", "filter": [ { "function": "custom", "filter_fn": "" } ] } ], "should_decontaminate": false, "gen_prefix": "Here is the completed function:\n```python\n{{ prompt }}\n", "metadata": { "version": 4.0, "base_url": "http://192.168.20.241:8888/v1/chat/completions", "model": "DeepSeek-v4.1-Flash-EXL3", "max_gen_toks": 1024, "temperature": 0, "num_ctx": 16384, "config_source": "/opt/bench/venv/lib/python3.13/site-packages/lm_eval/tasks/humaneval/humaneval_instruct.yaml" } }, "ifeval": { "task": "ifeval", "dataset_path": "google/IFEval", "test_split": "train", "doc_to_text": "prompt", "doc_to_target": 0, "unsafe_code": false, "process_results": "def process_results(doc, results):\n inp = InputExample(\n key=doc[\"key\"],\n instruction_id_list=doc[\"instruction_id_list\"],\n prompt=doc[\"prompt\"],\n kwargs=doc[\"kwargs\"],\n )\n response = results[0]\n\n out_strict = test_instruction_following_strict(inp, response)\n out_loose = test_instruction_following_loose(inp, response)\n\n return {\n \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n }\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "default", "split": null, "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "prompt", "doc_to_choice": null, "doc_to_target": 0, "gen_prefix": null, "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 0, "metric_list": [ { "metric": "prompt_level_strict_acc", "aggregation": "mean", "higher_is_better": true }, { "metric": "inst_level_strict_acc", "aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n", "higher_is_better": true }, { "metric": "prompt_level_loose_acc", "aggregation": "mean", "higher_is_better": true }, { "metric": "inst_level_loose_acc", "aggregation": "def agg_inst_level_acc(items):\n flat_items = [item for sublist in items for item in sublist]\n inst_level_acc = sum(flat_items) / len(flat_items)\n return inst_level_acc\n", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [], "do_sample": false, "temperature": 0.0, "max_gen_toks": 1280 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 4.0, "base_url": "http://192.168.20.241:8888/v1/chat/completions", "model": "DeepSeek-v4.1-Flash-EXL3", "max_gen_toks": 1024, "temperature": 0, "num_ctx": 16384, "config_source": "/opt/bench/venv/lib/python3.13/site-packages/lm_eval/tasks/ifeval/ifeval.yaml" } }, "mbpp_plus_instruct": { "task": "mbpp_plus_instruct", "dataset_path": "evalplus/mbppplus", "test_split": "test", "doc_to_text": "{{prompt if prompt is defined else text}} Your code should satisfy the following assertion:\n{{test_list[0]}}", "doc_to_target": "{{test_list[0]}}", "unsafe_code": true, "description": "", "target_delimiter": "", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": null, "process_docs": null, "fewshot_indices": null, "samples": "", "doc_to_text": "{{prompt if prompt is defined else text}} Your code should satisfy the following assertion:\n{{test_list[0]}}", "doc_to_choice": null, "doc_to_target": "{{test_list[0]}}", "gen_prefix": "Here is a solution to this programming problem:\n```python\n", "fewshot_delimiter": "\n\n", "target_delimiter": "" }, "num_fewshot": 0, "metric_list": [ { "metric": "def pass_at_1(\n references: Union[str, list[str]], predictions: Union[str, list[list[str]]]\n) -> float:\n if isinstance(references, str):\n references = [references]\n if isinstance(predictions[0], str):\n predictions = [[p] for p in predictions]\n return pass_at_k.compute(\n references=references,\n predictions=predictions,\n k=[1],\n )[0][\"pass@1\"]\n", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "max_gen_toks": 1024, "until": [], "do_sample": false }, "repeats": 1, "filter_list": [ { "name": "extract_code", "filter": [ { "function": "custom", "filter_fn": "" } ] } ], "should_decontaminate": false, "gen_prefix": "Here is a solution to this programming problem:\n```python\n", "metadata": { "version": 1.0, "base_url": "http://192.168.20.241:8888/v1/chat/completions", "model": "DeepSeek-v4.1-Flash-EXL3", "max_gen_toks": 1024, "temperature": 0, "num_ctx": 16384, "config_source": "/opt/bench/venv/lib/python3.13/site-packages/lm_eval/tasks/mbpp/mbpp_plus_instruct.yaml" } }, "minerva_math500": { "task": "minerva_math500", "dataset_path": "HuggingFaceH4/MATH-500", "dataset_name": "default", "test_split": "test", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n", "doc_to_target": "{{answer if few_shot is undefined else solution}}", "unsafe_code": false, "process_results": "def process_results(doc: dict, results: list[str]) -> dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n # math_verify\n _mvres = verify(\n gold=parse(doc[\"solution\"]),\n target=parse(candidates),\n )\n mathval = 1 if _mvres else 0\n\n res = {\n \"exact_match\": retval,\n \"math_verify\": mathval,\n }\n return res\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "split": null, "process_docs": "", "fewshot_indices": null, "samples": "", "doc_to_text": "", "doc_to_choice": null, "doc_to_target": "{{answer if few_shot is undefined else solution}}", "gen_prefix": null, "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 4, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true }, { "metric": "math_verify", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Problem:" ], "do_sample": false, "temperature": 0.0 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 3.1, "base_url": "http://192.168.20.241:8888/v1/chat/completions", "model": "DeepSeek-v4.1-Flash-EXL3", "max_gen_toks": 1024, "temperature": 0, "num_ctx": 16384, "config_source": "/opt/bench/venv/lib/python3.13/site-packages/lm_eval/tasks/minerva_math/minerva_math500.yaml" } } }, "versions": { "arc_challenge_chat": 1.0, "gsm8k_cot": 3.0, "humaneval_instruct": 4.0, "ifeval": 4.0, "mbpp_plus_instruct": 1.0, "minerva_math500": 3.1 }, "n-shot": { "arc_challenge_chat": 0, "gsm8k_cot": 8, "humaneval_instruct": 0, "ifeval": 0, "mbpp_plus_instruct": 0, "minerva_math500": 4 }, "higher_is_better": { "arc_challenge_chat": { "exact_match": true }, "gsm8k_cot": { "exact_match": true }, "humaneval_instruct": { "pass_at_k": true, "pass@1": true }, "ifeval": { "prompt_level_strict_acc": true, "inst_level_strict_acc": true, "prompt_level_loose_acc": true, "inst_level_loose_acc": true }, "mbpp_plus_instruct": { "pass_at_1": true }, "minerva_math500": { "exact_match": true, "math_verify": true } }, "n-samples": { "humaneval_instruct": { "original": 164, "effective": 164 }, "mbpp_plus_instruct": { "original": 378, "effective": 378 }, "gsm8k_cot": { "original": 1319, "effective": 1319 }, "minerva_math500": { "original": 500, "effective": 500 }, "arc_challenge_chat": { "original": 1172, "effective": 1172 }, "ifeval": { "original": 541, "effective": 541 } }, "config": { "model": "local-chat-completions", "model_args": { "base_url": "http://192.168.20.241:8888/v1/chat/completions", "model": "DeepSeek-v4.1-Flash-EXL3", "max_gen_toks": 1024, "temperature": 0, "num_ctx": 16384 }, "batch_size": "4", "batch_sizes": [], "device": "cuda:0", "use_cache": null, "limit": null, "bootstrap_iters": 100000, "gen_kwargs": {}, "random_seed": 0, "numpy_seed": 1234, "torch_seed": 1234, "fewshot_seed": 1234 }, "git_hash": null, "date": 1792533668.120967, "pretty_env_info": "PyTorch version: 2.14.1+cu130\nIs debug build: False\nCUDA used to build PyTorch: 13.0\nROCM used to build PyTorch: N/A\n\nOS: Debian GNU/Linux 13 (trixie) (x86_64)\nGCC version: (Debian 14.2.0-19) 14.2.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.41\n\nPython version: 3.13.5 (main, Aug 10 2026, 12:06:59) [GCC 14.2.0] (64-bit runtime)\nPython platform: Linux-6.14.11-1-pve-x86_64-with-glibc2.41\nIs CUDA available: False\nCUDA runtime version: No CUDA\nCUDA_MODULE_LOADING set to: N/A\nGPU models and configuration: No CUDA\nNvidia driver version: No CUDA\ncuDNN version: No CUDA\nIs XPU available: False\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: False\nCaching allocator config: N/A\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 16\nOn-line CPU(s) list: 3,4,7-9,12,14,15\nOff-line CPU(s) list: 0-2,5,6,10,11,13\nVendor ID: AuthenticAMD\nModel name: AMD Ryzen 7 8845HS w/ Radeon 780M Graphics\nCPU family: 25\nModel: 117\nThread(s) per core: 2\nCore(s) per socket: 8\nSocket(s): 1\nStepping: 2\nFrequency boost: enabled\nCPU(s) scaling MHz: 75%\nCPU max MHz: 5137.0000\nCPU min MHz: 400.0000\nBogoMIPS: 7586.31\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid overflow_recov succor smca fsrm flush_l1d\nVirtualization: AMD-V\nL1d cache: 256 KiB (8 instances)\nL1i cache: 256 KiB (8 instances)\nL2 cache: 8 MiB (8 instances)\nL3 cache: 16 MiB (1 instance)\nNUMA node(s): 1\nNUMA node0 CPU(s): 0-15\nVulnerability Gather data sampling: Not affected\nVulnerability Ghostwrite: Not affected\nVulnerability Indirect target selection: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; Safe RET\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-on; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] mypy_extensions==1.1.0\n[pip3] numpy==2.5.4\n[pip3] nvidia-cublas==13.1.1.3\n[pip3] nvidia-cuda-cupti==13.0.85\n[pip3] nvidia-cuda-nvrtc==13.0.88\n[pip3] nvidia-cuda-runtime==13.0.96\n[pip3] nvidia-cudnn-cu13==9.24.0.43\n[pip3] nvidia-cufft==12.0.0.61\n[pip3] nvidia-curand==10.4.0.35\n[pip3] nvidia-cusolver==12.0.4.66\n[pip3] nvidia-cusparse==12.6.3.3\n[pip3] nvidia-cusparselt-cu13==0.8.1\n[pip3] nvidia-nccl-cu13==2.30.7\n[pip3] nvidia-nvjitlink==13.4.92\n[pip3] nvidia-nvtx==13.0.85\n[pip3] torch==2.14.1\n[pip3] triton==3.8.0\n[conda] Could not collect", "transformers_version": "5.20.2", "lm_eval_version": "0.4.13", "upper_git_hash": null, "task_hashes": {}, "model_source": "local-chat-completions", "model_name": "DeepSeek-v4.1-Flash-EXL3", "model_name_sanitized": "DeepSeek-v4.1-Flash-EXL3", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": true, "chat_template": "", "chat_template_sha": null, "total_evaluation_time_seconds": "15421.663048956543" }