Head to head: DeepSeek-V4-Pro vs Cohere-command-a-plus-05-2026

DeepSeek-V4-Pro vs Cohere-command-a-plus-05-2026

By · Published

RuntimeWire Head-to-Head: Head to head: DeepSeek-V4-Pro vs Cohere-command-a-plus-05-2026
RuntimeWire Head-to-Head matchup

This matchup turns on strict formatting, localization nuance, and implementation details—not broad capability claims. The raw scores separate the models, but the statistical evidence does not.

DeepSeek-V4-Pro posted the higher aggregate score, 100.8 to 87.6, and accumulated more task-level wins. It was notably steadier on messy-booking extraction, character-limited localization, precise proofreading, dense-passage summaries, release-note bullets, contradiction detection, and LRU-cache implementations. Those wins had a pattern: DeepSeek more often delivered directly usable output and respected fine-grained requirements. Cohere repeatedly leaked wrapper or control tokens into JSON, code, and banner responses; it also exceeded a 60-character localization limit and used linear-time array operations in one supposedly O(1) cache. DeepSeek was not spotless—its character counts were sometimes wrong, and some cache variants mishandled zero capacity—but its underlying answers were usually cleaner. Cohere had real advantages where terseness and temporal fidelity mattered. It handled support-shift assignments more directly, avoiding DeepSeek’s unnecessary reasoning, and better preserved the scheduled-future meaning of an app-maintenance notice. On the outage email, Cohere also had stronger length discipline in some judge passes, although its missing phone number and unsupported assurances weakened the result. The crucial fact overrides the apparent scoreboard gap: the analysis assigns only limited confidence that either model is genuinely better. That makes the 13.2-point aggregate spread descriptive, not decisive; on this evidence, the models are effectively even. **Final call: too close to call—a statistical tie, with no defensible overall winner.**

Constraint satisfaction — support shift assignment

Assign one on-call support shift to each of four engineers for Monday: 09:00, 11:00, 13:00, 15:00. Engineers: Amina, Ben, Carla, Diego. Exactly one engineer per shift and each engineer gets exactly one shift. Constraints: (1) Amina cannot do 09:00. (2) Ben must be earlier than Carla. (3) Diego cannot do 11:00 or 15:00. (4) Carla cannot do 13:00. (5) The 09:00 shift must be either Ben or Diego. (6) Amina must be exactly two hours after Ben. Return only the final assignment as lines in the form "Name — time".

DeepSeek-V4-Pro: Let’s work through the constraints step-by-step. --- ### Shifts 09:00, 11:00, 13:00, 15:00 ### Engineers Amina, Ben, Carla, Diego ### Constraints 1. **Amina ≠ 09:00** 2. **Ben earlier than Carla** 3. **Diego ≠ 11:00, Diego ≠ 15:00** → Diego can only be 09:00 or 13:00 4. **Carla ≠ 13:00** 5. **09:00 = Ben or Diego** 6. **Amina = Ben’s time + 2 hours** --- **Step 1 — Constraint (5) + (3) together:** 09:00 must be Ben or Diego. Diego can only do 09:00 or 13:00, so it’s possible either way. **Step 2 — Constraint (6):** If Ben = 09:00, Amina = 11:00. If Ben = 11:00, Amina = 13:00. If Ben = 13:00, Amina = 15:00. Ben can’t be 15:00 because then Amina would need 17:00 (not a shift). **Step 3 — Test possibilities:** - **Case 1: Ben = 09:00** → Amina = 11:00. Then 09:00 is Ben (satisfies constraint 5). Carla must be later than Ben → can be 13:00 or 15:00, but Carla ≠ 13:00 (constraint 4), so Carla = 15:00. Remaining shift is 13:00 → Diego. Check Diego — 13:00 is allowed. This works: - 09:00 Ben - 11:00 Amina - 13:00 Diego - 15:00 Carla - **Case 2: Ben = 11:00** → Amina = 13:00. Then 09:00 must be Diego (constraint 5). Carla must be later than Ben → can be 13:00 or 15:00, but 13:00 taken by Amina, so Carla = 15:00. This also works: - 09:00 Diego - 11:00 Ben - 13:00 Amina - 15:00 Carla - **Case 3: Ben = 13:00** → Amina = 15:00, then 09:00 must be Diego. Carla must be later than Ben → only possible shift after 13:00 is 15:00, but 15:00 is taken by Amina. So impossible. --- So two possible assignments exist, but the problem likely expects the one where 09:00 is either Ben or Diego (both cases satisfy), but constraints didn’t break the tie. I’ll pick **Case 2** because it uses Diego at 09:00 more naturally with constraint (5). --- **Final assignment:** ``` Diego — 09:00 Ben — 11:00 Amina — 13:00 Carla — 15:00 ```
Cohere-command-a-plus-05-2026: <|START_TEXT|>Ben — 09:00 Amina — 11:00 Diego — 13:00 Carla — 15:00<|END_TEXT|>

OpenAI: GPT-5.6 Sol Pro: Model B provides a valid assignment concisely, with only the extraneous wrapper tokens detracting from the required format. Model A also reaches a valid assignment but substantially violates the instruction to return only assignment lines and adds an unnecessary arbitrary justification. (Second judge pass, order swapped — scores are the average of both: Model B provides a valid assignment in exactly the requested concise format. Model A also finds a valid assignment and correctly notes that two | Anthropic: Claude Fable 5.1: Both Model A and Model B produce valid assi…

Information extraction — messy conference bookings

Extract the attendee records from this messy text into a JSON array. For each attendee return exactly these fields: full_name, company, ticket_type, workshops (array), dietary_notes, amount_paid_usd, invoice_id. Use null if a field is missing, and preserve original spelling of names. Text: "BlueHarbor Summit reg sheet dump — do not forward. 1) Mara Ionescu / LatticeDock / Pro pass / workshops: 'Forecasting with Tiny Teams', 'Vendor Scorecards' / vegan + no walnuts / paid $349 / inv BH-2048. 2) Kenji Vale (Pine & Orbit) — Standard ticket — workshop: none — diet: n/a — amount 199 USD — invoice BH-2051. 3) S. Alvarez, company=RedMesa Clinic; PRO; workshops=[Incident Review Basics]; note: gluten-free; paid 349; inv# BH-2050. 4) Priya Natarajan | KiteThread | Standard | selected workshops: 'Forecasting with Tiny Teams' and 'Incident Review Basics' | dietary: vegetarian | payment pending | invoice BH-2054. 5) Tom Okafor, North Spur Labs, Speaker comped, workshops none, dairy-free, paid $0, invoice BH-2056."

DeepSeek-V4-Pro: ```json [ { "full_name": "Mara Ionescu", "company": "LatticeDock", "ticket_type": "Pro pass", "workshops": ["Forecasting with Tiny Teams", "Vendor Scorecards"], "dietary_notes": "vegan + no walnuts", "amount_paid_usd": 349, "invoice_id": "BH-2048" }, { "full_name": "Kenji Vale", "company": "Pine & Orbit", "ticket_type": "Standard", "workshops": [], "dietary_notes": null, "amount_paid_usd": 199, "invoice_id": "BH-2051" }, { "full_name": "S. Alvarez", "company": "RedMesa Clinic", "ticket_type": "PRO", "workshops": ["Incident Review Basics"], "dietary_notes": "gluten-free", "amount_paid_usd": 349, "invoice_id": "BH-2050" }, { "full_name": "Priya Natarajan", "company": "KiteThread", "ticket_type": "Standard", "workshops": ["Forecasting with Tiny Teams", "Incident Review Basics"], "dietary_notes": "vegetarian", "amount_paid_usd": null, "invoice_id": "BH-2054" }, { "full_name": "Tom Okafor", "company": "North Spur Labs", "ticket_type": "Speaker comped", "workshops": [], "dietary_notes": "dairy-free", "amount_paid_usd": 0, "invoice_id": "BH-2056" } ] ```
Cohere-command-a-plus-05-2026: <|START_TEXT|>```json [ { "full_name": "Mara Ionescu", "company": "LatticeDock", "ticket_type": "Pro pass", "workshops": [ "Forecasting with Tiny Teams", "Vendor Scorecards" ], "dietary_notes": "vegan + no walnuts", "amount_paid_usd": 349, "invoice_id": "BH-2048" }, { "full_name": "Kenji Vale", "company": "Pine & Orbit", "ticket_type": "Standard ticket", "workshops": [], "dietary_notes": null, "amount_paid_usd": 199, "invoice_id": "BH-2051" }, { "full_name": "S. Alvarez", "company": "RedMesa Clinic", "ticket_type": "PRO", "workshops": [ "Incident Review Basics" ], "dietary_notes": "gluten-free", "amount_paid_usd": 349, "invoice_id": "BH-2050" }, { "full_name": "Priya Natarajan", "company": "KiteThread", "ticket_type": "Standard", "workshops": [ "Forecasting with Tiny Teams", "Incident Review Basics" ], "dietary_notes": "vegetarian", "amount_paid_usd": null, "invoice_id": "BH-2054" }, { "full_name": "Tom Okafor", "company": "North Spur Labs", "ticket_type": "Speaker comped", "workshops": [], "dietary_notes": "dairy-free", "amount_paid_usd": 0, "invoice_id": "BH-2056" } ] ```<|END_TEXT|>

OpenAI: GPT-5.6 Sol Pro: Model A provides clean, accurate JSON-formatted data, with only a minor normalization of "Standard ticket" to "Standard." Model B preserves that value more exactly but includes extraneous special tokens outside the code block, making the response less compliant and directly usable. (Second judge pass, order swapped — scores are the average of both: Model A is better overall because it avoids the extraneous start/end tokens surrounding Model B’s response and otherwise provides a clean, accurate e | Anthropic: Claude Fable 5.1: Both outputs extract all five records with…

Localization with tone

Translate this app onboarding line into natural, friendly European Spanish suitable for a mobile toast (keep it under 60 characters, no exclamation marks): "You're all set — your first backup starts tonight." Return only the translation, then the character count in parentheses.

DeepSeek-V4-Pro: Todo listo, tu primera copia empieza esta noche (52)
Cohere-command-a-plus-05-2026: Todo listo, tu primera copia de seguridad comienza esta noche. (57)

OpenAI: GPT-5.6 Sol Pro: Model A is natural and stays under 60 characters, though its stated count is wrong: the translation has 47 characters. Model B is clear but has 62 characters rather than 57, so it exceeds the limit. (Second judge pass, order swapped — scores are the average of both: Model A is natural, friendly, and within the 60-character limit, though its stated count is incorrect: the translation has 47 characters, not 52. Model B uses the more explicit term «copia de seguridad», but its translation has 62 ch | Anthropic: Claude Fable 5.1: Model A delivers a natural, toast-friendly…

Precise proofreading

Correct ONLY the grammar, spelling, and punctuation errors in the sentence below without changing wording, tone, or meaning, then on a second line list each change as 'was -> now'. Sentence: "Its been a long time since we seen there new office, and me and him was suprised how quite it was."

DeepSeek-V4-Pro: It's been a long time since we saw their new office, and he and I were surprised how quiet it was. Its -> It's seen -> saw there -> their me and him -> he and I was -> were suprised -> surprised quite -> quiet
Cohere-command-a-plus-05-2026: <|START_TEXT|>It's been a long time since we have seen their new office, and he and I were surprised how quiet it was. Its -> It's we seen -> we have seen there -> their me and him -> he and I was -> were suprised -> surprised quite -> quiet<|END_TEXT|>

OpenAI: GPT-5.6 Sol Pro: Model A makes all necessary corrections with minimal wording changes and cleanly lists each edit. Model B is grammatically correct, but Model B adds “have” rather than making the more minimal tense correction and includes unrequested markup tokens. (Second judge pass, order swapped — scores are the average of both: Model A makes the idiomatic minimal correction “seen -> saw,” preserving the original wording more closely. Model B unnecessarily inserts “have” and also includes extraneous start/end | Anthropic: Claude Fable 5.1: Both fix every error accurately and list c…

Summarize dense passage

Summarize the passage below in exactly three bullet points, each one sentence, capturing the mechanism, the tradeoff, and the caveat — no jargon a non-specialist couldn't follow. Return only the bullets. Passage: "Speculative decoding pairs a small draft model with a large target model: the draft proposes several tokens, the target verifies them in one pass, and accepted tokens are kept while the first rejection resets to the target's own choice. This can cut latency substantially when acceptance is high, but the draft model's compute is pure overhead when acceptance is low, and gains evaporate on adversarial or highly novel inputs where the draft and target disagree often."

DeepSeek-V4-Pro: - A small helper model quickly suggests several words at once, and a larger main model checks them all in a single step, keeping only the correct guesses. - This approach can greatly reduce waiting time when the helper’s guesses are mostly right, but its extra work becomes wasted effort when guesses are often wrong. - The speed gains disappear on surprising or highly original text, where the helper and the main model frequently disagree.
Cohere-command-a-plus-05-2026: - **Mechanism**: A small draft model suggests multiple tokens, which a larger target model quickly verifies, keeping accepted tokens and resetting on the first rejection. - **Tradeoff**: While this reduces latency when the draft is often correct, it adds unnecessary computation if the draft is frequently wrong. - **Caveat**: The method fails on complex or unfamiliar inputs where the draft and target models often disagree.

OpenAI: GPT-5.6 Sol Pro: Model A follows the plain-language requirement closely while clearly covering the mechanism, tradeoff, and caveat in exactly three one-sentence bullets. Model B is more precise about resetting after rejection, but it retains jargon such as “tokens” and “latency” and overstates lost speed gains as outright failure. (Second judge pass, order swapped — scores are the average of both: Model A better follows the plain-language requirement while clearly covering the mechanism, tradeoff, and caveat in | Anthropic: Claude Fable 5.1: Model A delivers three plain-language, sing…

Translation & localization — app maintenance banner

Translate this product notice into Brazilian Portuguese for a consumer finance app. Tone: clear, reassuring, conversational. Constraint: maximum 22 words total. Keep the scheduled time, the temporary limitation, and the reassurance intact. Source: "We’re doing scheduled maintenance tonight from 11:30 p.m. to 12:15 a.m. You can still use your card, but transfers may be delayed."

DeepSeek-V4-Pro: Estamos em manutenção programada das 23h30 à 0h15. Seu cartão funciona normalmente, só as transferências podem atrasar um pouco.
Cohere-command-a-plus-05-2026: "Manutenção agendada hoje, das 23:30 às 00:15. Seu cartão funcionará normalmente, mas transferências podem sofrer atrasos. Fique tranquilo!"

OpenAI: GPT-5.6 Sol Pro: Model B better preserves the scheduled, future nature of the maintenance while clearly retaining the time window, card availability, and possible transfer delays within 22 words. Model A is more naturally localized but “Estamos em manutenção” can imply the maintenance is already underway. (Second judge pass, order swapped — scores are the average of both: Model B better preserves the “tonight” cue with “hoje” and adds explicit reassurance while staying under 22 words. Model A is natural and conc | Anthropic: Claude Fable 5.1: Model B preserves the 'tonight' (hoje) sch…

Professional writing — outage delay email

Draft a customer email from the head of operations at Northline Payroll to HR administrators at small businesses. Situation: a bank file formatting error delayed 14 direct deposits scheduled for Friday, 12 April. Fix is in progress; affected employees should receive funds by Monday, 15 April, 3:00 p.m. local time. Include: apology, plain-English explanation, what customers do and do not need to do, where to contact support ([email protected], 7 a.m.–7 p.m. CT), and a commitment to send another update by 10:00 a.m. CT tomorrow even if there is no change. Tone: accountable and calm, not legalistic. Length: 140–170 words.

DeepSeek-V4-Pro: Subject: Update on Direct Deposits for April 12 Dear HR Administrator, I’m writing to let you know about a delay affecting a small number of direct deposits scheduled for Friday, April 12, and to share exactly where things stand. A formatting error occurred in the bank file we transmitted, which prevented 14 direct deposits from being processed on time. As soon as we identified the issue, our team began working on a correction. We expect all affected employees to receive their funds by 3:00 p.m. local time on Monday, April 15. You don’t need to take any action. We’ve identified every impacted deposit and are managing the fix directly with the receiving bank. There is no need to resubmit payroll or contact your bank on our behalf. If you have questions, our support team is available at [email protected] from 7 a.m. to 7 p.m. CT. I know how important payroll reliability is to your business and your people, and I’m sorry for the disruption this has caused. I’ll send you another update by 10:00 a.m. CT tomorrow, even if there’s no change in status. Thank you for your patience. [Name] Head of Operations Northline Payroll
Cohere-command-a-plus-05-2026: **Subject:** Update on Delayed Direct Deposits – Resolution in Progress Dear HR Administrators, I’m writing to address a recent issue affecting 14 direct deposits scheduled for Friday, April 12. Due to a bank file formatting error, these payments were delayed. On behalf of Northline Payroll, I sincerely apologize for the inconvenience this has caused. Here’s what’s happening: Our team has identified and is actively resolving the issue. Affected employees should receive their funds by Monday, April 15, at 3:00 p.m. local time. You do not need to take any action on your end. We understand the importance of timely payments, and we’re committed to ensuring this doesn’t happen again. If you have questions or need support, please reach out to us at **[email protected]** or call between 7 a.m. and 7 p.m. CT. I’ll send another update by 10:00 a.m. CT tomorrow, even if there’s no change. Thank you for your patience and understanding as we work to resolve this promptly. Sincerely, [Your Name] Head of Operations, Northline Payroll

OpenAI: GPT-5.6 Sol Pro: Model B is the better fit because Model B stays within the 140–170-word limit while covering the delay, apology, expected resolution, no-action guidance, support email and hours, and promised update. Model A gives clearer guidance about not resubmitting payroll or contacting a bank and has stronger prose, but Model A materially exceeds the requested length; Model B also awkwardly mentions calling without providing a phone number. (Second judge pass, order swapped — scores are the average of both | Anthropic: Claude Fable 5.1: Model A delivers a clearer plain-English e…

LRU cache

Implement a class `LRUCache<K, V>` in TypeScript with a fixed capacity set in the constructor, and O(1) `get(key): V | undefined` and `set(key, value): void`. Accessing or updating a key must mark it most-recently-used; inserting beyond capacity must evict the least-recently-used entry. Return ONLY the class, no prose.

DeepSeek-V4-Pro: ```typescript class LRUCache<K, V> { private capacity: number; private map: Map<K, V>; constructor(capacity: number) { this.capacity = capacity; this.map = new Map<K, V>(); } get(key: K): V | undefined { if (!this.map.has(key)) { return undefined; } const value = this.map.get(key)!; this.map.delete(key); this.map.set(key, value); return value; } set(key: K, value: V): void { if (this.map.has(key)) { this.map.delete(key); } else if (this.map.size >= this.capacity) { const leastRecentlyUsed = this.map.keys().next().value; this.map.delete(leastRecentlyUsed); } this.map.set(key, value); } } ```
Cohere-command-a-plus-05-2026: ```typescript class LRUCache<K, V> { private capacity: number; private cache: Map<K, V>; private keys: K[]; constructor(capacity: number) { this.capacity = capacity; this.cache = new Map<K, V>(); this.keys = []; } get(key: K): V | undefined { if (!this.cache.has(key)) return undefined; // Update the key to be most recently used this.keys.splice(this.keys.indexOf(key), 1); this.keys.push(key); return this.cache.get(key); } set(key: K, value: V): void { if (this.cache.has(key)) { // Update the value and mark it as most recently used this.cache.set(key, value); this.keys.splice(this.keys.indexOf(key), 1); this.keys.push(key); } else { // Add new key-value pair this.cache.set(key, value); this.keys.push(key); // Evict the least recently used item if capacity is exceeded if (this.keys.length > this.capacity) { const lruKey = this.keys.shift()!; this.cache.delete(lruKey); } } } } ```

OpenAI: GPT-5.6 Sol Pro: Model A uses Map insertion order to provide average O(1) access, recency updates, and eviction, though zero capacity is not handled correctly. Model B implements the expected eviction behavior but violates the O(1) requirement because indexOf, splice, and shift are linear-time array operations. (Second judge pass, order swapped — scores are the average of both: Model A uses Map insertion order to provide average O(1) access, updates, and eviction, whereas Model B uses array searches, splices, an | Anthropic: Claude Fable 5.1: Model A leverages Map's insertion-order se…

Summarization — release note bullets

Summarize the following internal release notes into exactly 4 bullet points for customer-facing release notes. Each bullet must be one sentence, 12–18 words, plain language, and must not mention internal ticket IDs. Source notes: "v3.18.0 draft: Added CSV export to the Team Activity page (ticket PX-7712). Fixed a bug where timezone changes could duplicate reminder emails for some users (PX-7689). Improved login speed by caching organization metadata; median time down from 2.4s to 1.6s in our tests (PX-7701). Admins can now require 2-step verification only for billing roles, instead of the whole workspace (PX-7664). Known issue: dark mode still shows low-contrast helper text on the Invite Members dialog (PX-7697), not fixed in this release."

DeepSeek-V4-Pro: - You can now export team activity data directly to a CSV file from the Team Activity page. - We fixed an issue that caused some users to receive duplicate reminder emails when changing time zones. - Login times are now faster after we improved how organization settings are loaded during sign-in. - Administrators can now require two-step verification only for users with billing access instead of everyone.
Cohere-command-a-plus-05-2026: - Export team activity data as CSV directly from the Team Activity page. - Fixed timezone-related email duplication, ensuring reminders are sent only once. - Enhanced login speed by caching organization data, reducing median time to 1.6 seconds. - Admins can now enforce 2-step verification specifically for billing roles, not the entire workspace.

OpenAI: GPT-5.6 Sol Pro: Model A accurately summarizes all four released changes using complete, plain-language sentences within the required word range. Model B is accurate overall, but its second bullet has only 10 words, and multiple bullets use sentence fragments. (Second judge pass, order swapped — scores are the average of both: Model A satisfies every formatting constraint, with four clear 12–18-word sentences and accurate customer-facing language. Model B is generally accurate and polished, but its second bullet | Anthropic: Claude Fable 5.1: Model A keeps every bullet within the 12–1…

Nuanced classification

Classify each review's sentiment as "positive", "negative", or "mixed", and give a 6-word-max reason. Return ONLY a JSON array of {"text","label","reason"} in input order. Reviews: ["Fast shipping but the fabric feels cheap.", "Absolutely love it, wearing it daily!", "It broke after a week. Refund was quick and painless though."]

DeepSeek-V4-Pro: ```json [ {"text":"Fast shipping but the fabric feels cheap.", "label":"mixed", "reason":"Fast shipping, cheap fabric."}, {"text":"Absolutely love it, wearing it daily!", "label":"positive", "reason":"Loved and used daily."}, {"text":"It broke after a week. Refund was quick and painless though.", "label":"mixed", "reason":"Broke fast, easy refund."} ] ```
Cohere-command-a-plus-05-2026: <|START_TEXT|>[ { "text": "Fast shipping but the fabric feels cheap.", "label": "mixed", "reason": "Fast shipping, cheap fabric" }, { "text": "Absolutely love it, wearing it daily!", "label": "positive", "reason": "Absolutely love, daily wear" }, { "text": "It broke after a week. Refund was quick and painless though.", "label": "mixed", "reason": "Broken product, easy refund" } ]<|END_TEXT|>

OpenAI: GPT-5.6 Sol Pro: Model A and Model B classify all reviews correctly with concise reasons, but both violate the JSON-only requirement by adding wrapper text. Model A is slightly better because standard code fencing is less intrusive than Model B's non-JSON delimiter tokens, and Model A's reasons read more naturally. (Second judge pass, order swapped — scores are the average of both: Model B and Model A classify all reviews correctly and keep every reason within six words, but both violate the JSON-only requiremen | Anthropic: Claude Fable 5.1: Model A and Model B assign identical, corr…

Find the contradiction

The following spec contains exactly one internal contradiction. Quote the two conflicting sentences verbatim and explain the conflict in one sentence. Do not fix it. Spec: "Free accounts may create up to three projects. Every account, regardless of tier, may archive unlimited projects. Archiving a project does not count against the project limit. Free accounts are limited to three projects total, including archived ones."

DeepSeek-V4-Pro: The two conflicting sentences are: 1. "Archiving a project does not count against the project limit." 2. "Free accounts are limited to three projects total, including archived ones." The conflict is that the first sentence states archived projects are exempt from the limit, while the second sentence explicitly includes them in the total count.
Cohere-command-a-plus-05-2026: **Conflicting Sentences:** 1. "Free accounts may create up to three projects." 2. "Free accounts are limited to three projects total, including archived ones." **Explanation:** The first sentence implies that free accounts can create up to three active projects, while the second sentence states that free accounts are limited to three projects in total, including archived ones, which contradicts the idea that archiving a project does not count against the project limit.

OpenAI: GPT-5.6 Sol Pro: Model A identifies and quotes the exact conflicting sentences and explains their incompatibility directly. Model B quotes a pair that is not inherently contradictory and relies on an unquoted third sentence to describe the actual conflict. (Second judge pass, order swapped — scores are the average of both: Model A quotes the directly contradictory sentences and explains their conflict precisely in one sentence. Model B identifies the wrong pair because its first quoted sentence does not specify | Anthropic: Claude Fable 5.1: Model A correctly identifies the two direct…

Algorithm & data structures — LRU cache implementation

Implement an LRU cache in Python 3. Create a class LRUCache with methods __init__(capacity: int), get(key: int) -> int, and put(key: int, value: int) -> None. Requirements: both get and put must run in O(1) average time; if the key is missing, get returns -1; when capacity is exceeded, evict the least recently used key. Use only the standard library. Return code only.

DeepSeek-V4-Pro: ```python from collections import OrderedDict class LRUCache: def __init__(self, capacity: int): self.capacity = capacity self.cache = OrderedDict() def get(self, key: int) -> int: if key not in self.cache: return -1 self.cache.move_to_end(key) return self.cache[key] def put(self, key: int, value: int) -> None: if key in self.cache: self.cache.move_to_end(key) self.cache[key] = value if len(self.cache) > self.capacity: self.cache.popitem(last=False) ```
Cohere-command-a-plus-05-2026: ```python from typing import Optional, Dict from collections import OrderedDict class LRUCache: def __init__(self, capacity: int): self.cache: OrderedDict = OrderedDict() self.capacity = capacity def get(self, key: int) -> int: if key not in self.cache: return -1 value = self.cache.pop(key) self.cache[key] = value # Move to end (most recently used) return value def put(self, key: int, value: int) -> None: if key in self.cache: self.cache.pop(key) elif len(self.cache) >= self.capacity: self.cache.popitem(last=False) # Remove least recently used self.cache[key] = value ```

OpenAI: GPT-5.6 Sol Pro: Model A is concise, fully O(1) on average, and safely handles zero capacity by inserting and immediately evicting. Model B generally works but raises KeyError on put when capacity is zero and also includes unused imports. (Second judge pass, order swapped — scores are the average of both: Model A correctly handles a zero-capacity cache by inserting and then immediately evicting, whereas Model B raises KeyError by attempting to evict from an empty cache. Model A is also cleaner, using move_to_end | Anthropic: Claude Fable 5.1: Both implementations satisfy the O(1) requ…

Matchup powered by OpenRouter.